Hugging Face's logo

mlx-community
/
VibeVoice-Realtime-0.5B-8bit

Text-to-Speech
Transformers
Safetensors
MLX
English
vibevoice_streaming
Realtime TTS
Streaming text input
Long-form speech generation
8-bit precision
Model card Files
xet
Community
prince-canuma commited on
Commit
5fcbe22
·
verified ·
1 Parent(s): f604f77

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +27 -0
  2. config.json +96 -0
  3. model.safetensors +3 -0
  4. model.safetensors.index.json +1105 -0
  5. preprocessor_config.json +13 -0
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ pipeline_tag: text-to-speech
6
+ tags:
7
+ - Realtime TTS
8
+ - Streaming text input
9
+ - Long-form speech generation
10
+ - mlx
11
+ library_name: transformers
12
+ base_model:
13
+ - Qwen/Qwen2.5-0.5B
14
+ ---
15
+
16
+ # mlx-community/VibeVoice-Realtime-0.5B-8bit
17
+ This model was converted to MLX format from [`microsoft/VibeVoice-Realtime-0.5B`](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) using mlx-audio version **0.2.6**.
18
+ Refer to the [original model card](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) for more details on the model.
19
+ ## Use with mlx
20
+
21
+ ```bash
22
+ pip install -U mlx-audio
23
+ ```
24
+
25
+ ```bash
26
+ python -m mlx_audio.tts.generate --model mlx-community/VibeVoice-Realtime-0.5B-8bit --text "Describe this image."
27
+ ```
config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "acoustic_tokenizer_config": {
3
+ "causal": true,
4
+ "channels": 1,
5
+ "conv_bias": true,
6
+ "conv_norm": "none",
7
+ "corpus_normalize": 0.0,
8
+ "decoder_depths": null,
9
+ "decoder_n_filters": 32,
10
+ "decoder_ratios": [
11
+ 8,
12
+ 5,
13
+ 5,
14
+ 4,
15
+ 2,
16
+ 2
17
+ ],
18
+ "disable_last_norm": true,
19
+ "encoder_depths": "3-3-3-3-3-3-8",
20
+ "encoder_n_filters": 32,
21
+ "encoder_ratios": [
22
+ 8,
23
+ 5,
24
+ 5,
25
+ 4,
26
+ 2,
27
+ 2
28
+ ],
29
+ "fix_std": 0.5,
30
+ "layer_scale_init_value": 1e-06,
31
+ "layernorm": "RMSNorm",
32
+ "layernorm_elementwise_affine": true,
33
+ "layernorm_eps": 1e-05,
34
+ "mixer_layer": "depthwise_conv",
35
+ "model_type": "vibevoice_acoustic_tokenizer",
36
+ "pad_mode": "constant",
37
+ "std_dist_type": "gaussian",
38
+ "vae_dim": 64,
39
+ "weight_init_value": 0.01
40
+ },
41
+ "acoustic_vae_dim": 64,
42
+ "architectures": [
43
+ "VibeVoiceStreamingForConditionalGenerationInference"
44
+ ],
45
+ "decoder_config": {
46
+ "attention_dropout": 0.0,
47
+ "hidden_act": "silu",
48
+ "hidden_size": 896,
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 4864,
51
+ "max_position_embeddings": 8192,
52
+ "max_window_layers": 24,
53
+ "model_type": "qwen2",
54
+ "num_attention_heads": 14,
55
+ "num_hidden_layers": 24,
56
+ "num_key_value_heads": 2,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": null,
61
+ "tie_word_embeddings": false,
62
+ "torch_dtype": "bfloat16",
63
+ "use_cache": true,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 151936
66
+ },
67
+ "diffusion_head_config": {
68
+ "ddpm_batch_mul": 4,
69
+ "ddpm_beta_schedule": "cosine",
70
+ "ddpm_num_inference_steps": 20,
71
+ "ddpm_num_steps": 1000,
72
+ "diffusion_type": "ddpm",
73
+ "head_ffn_ratio": 3.0,
74
+ "head_layers": 4,
75
+ "hidden_size": 896,
76
+ "latent_size": 64,
77
+ "model_type": "vibevoice_diffusion_head",
78
+ "prediction_type": "v_prediction",
79
+ "rms_norm_eps": 1e-05,
80
+ "speech_vae_dim": 64
81
+ },
82
+ "model_type": "vibevoice_streaming",
83
+ "quantization": {
84
+ "group_size": 64,
85
+ "bits": 8,
86
+ "mode": "affine"
87
+ },
88
+ "quantization_config": {
89
+ "group_size": 64,
90
+ "bits": 8,
91
+ "mode": "affine"
92
+ },
93
+ "torch_dtype": "bfloat16",
94
+ "transformers_version": "4.51.3",
95
+ "tts_backbone_num_hidden_layers": 20
96
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6fef128bade2f818ca2cff8168749407297a02d0d2fa9e2905181df42fa22b
3
+ size 1120555546
model.safetensors.index.json ADDED
@@ -0,0 +1,1105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1120420848,
4
+ "total_parameters": 1017581858
5
+ },
6
+ "weight_map": {
7
+ "acoustic_connector.fc1.bias": "model.safetensors",
8
+ "acoustic_connector.fc1.biases": "model.safetensors",
9
+ "acoustic_connector.fc1.scales": "model.safetensors",
10
+ "acoustic_connector.fc1.weight": "model.safetensors",
11
+ "acoustic_connector.fc2.bias": "model.safetensors",
12
+ "acoustic_connector.fc2.biases": "model.safetensors",
13
+ "acoustic_connector.fc2.scales": "model.safetensors",
14
+ "acoustic_connector.fc2.weight": "model.safetensors",
15
+ "acoustic_connector.norm.weight": "model.safetensors",
16
+ "acoustic_tokenizer.decoder.head.conv.conv.bias": "model.safetensors",
17
+ "acoustic_tokenizer.decoder.head.conv.conv.weight": "model.safetensors",
18
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear1.bias": "model.safetensors",
19
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear1.biases": "model.safetensors",
20
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear1.scales": "model.safetensors",
21
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear1.weight": "model.safetensors",
22
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear2.bias": "model.safetensors",
23
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear2.biases": "model.safetensors",
24
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear2.scales": "model.safetensors",
25
+ "acoustic_tokenizer.decoder.stages.0.0.ffn.linear2.weight": "model.safetensors",
26
+ "acoustic_tokenizer.decoder.stages.0.0.ffn_gamma": "model.safetensors",
27
+ "acoustic_tokenizer.decoder.stages.0.0.ffn_norm.weight": "model.safetensors",
28
+ "acoustic_tokenizer.decoder.stages.0.0.gamma": "model.safetensors",
29
+ "acoustic_tokenizer.decoder.stages.0.0.mixer.conv.conv.conv.bias": "model.safetensors",
30
+ "acoustic_tokenizer.decoder.stages.0.0.mixer.conv.conv.conv.weight": "model.safetensors",
31
+ "acoustic_tokenizer.decoder.stages.0.0.norm.weight": "model.safetensors",
32
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear1.bias": "model.safetensors",
33
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear1.biases": "model.safetensors",
34
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear1.scales": "model.safetensors",
35
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear1.weight": "model.safetensors",
36
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear2.bias": "model.safetensors",
37
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear2.biases": "model.safetensors",
38
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear2.scales": "model.safetensors",
39
+ "acoustic_tokenizer.decoder.stages.0.1.ffn.linear2.weight": "model.safetensors",
40
+ "acoustic_tokenizer.decoder.stages.0.1.ffn_gamma": "model.safetensors",
41
+ "acoustic_tokenizer.decoder.stages.0.1.ffn_norm.weight": "model.safetensors",
42
+ "acoustic_tokenizer.decoder.stages.0.1.gamma": "model.safetensors",
43
+ "acoustic_tokenizer.decoder.stages.0.1.mixer.conv.conv.conv.bias": "model.safetensors",
44
+ "acoustic_tokenizer.decoder.stages.0.1.mixer.conv.conv.conv.weight": "model.safetensors",
45
+ "acoustic_tokenizer.decoder.stages.0.1.norm.weight": "model.safetensors",
46
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear1.bias": "model.safetensors",
47
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear1.biases": "model.safetensors",
48
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear1.scales": "model.safetensors",
49
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear1.weight": "model.safetensors",
50
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear2.bias": "model.safetensors",
51
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear2.biases": "model.safetensors",
52
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear2.scales": "model.safetensors",
53
+ "acoustic_tokenizer.decoder.stages.0.2.ffn.linear2.weight": "model.safetensors",
54
+ "acoustic_tokenizer.decoder.stages.0.2.ffn_gamma": "model.safetensors",
55
+ "acoustic_tokenizer.decoder.stages.0.2.ffn_norm.weight": "model.safetensors",
56
+ "acoustic_tokenizer.decoder.stages.0.2.gamma": "model.safetensors",
57
+ "acoustic_tokenizer.decoder.stages.0.2.mixer.conv.conv.conv.bias": "model.safetensors",
58
+ "acoustic_tokenizer.decoder.stages.0.2.mixer.conv.conv.conv.weight": "model.safetensors",
59
+ "acoustic_tokenizer.decoder.stages.0.2.norm.weight": "model.safetensors",
60
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear1.bias": "model.safetensors",
61
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear1.biases": "model.safetensors",
62
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear1.scales": "model.safetensors",
63
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear1.weight": "model.safetensors",
64
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear2.bias": "model.safetensors",
65
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear2.biases": "model.safetensors",
66
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear2.scales": "model.safetensors",
67
+ "acoustic_tokenizer.decoder.stages.0.3.ffn.linear2.weight": "model.safetensors",
68
+ "acoustic_tokenizer.decoder.stages.0.3.ffn_gamma": "model.safetensors",
69
+ "acoustic_tokenizer.decoder.stages.0.3.ffn_norm.weight": "model.safetensors",
70
+ "acoustic_tokenizer.decoder.stages.0.3.gamma": "model.safetensors",
71
+ "acoustic_tokenizer.decoder.stages.0.3.mixer.conv.conv.conv.bias": "model.safetensors",
72
+ "acoustic_tokenizer.decoder.stages.0.3.mixer.conv.conv.conv.weight": "model.safetensors",
73
+ "acoustic_tokenizer.decoder.stages.0.3.norm.weight": "model.safetensors",
74
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear1.bias": "model.safetensors",
75
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear1.biases": "model.safetensors",
76
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear1.scales": "model.safetensors",
77
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear1.weight": "model.safetensors",
78
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear2.bias": "model.safetensors",
79
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear2.biases": "model.safetensors",
80
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear2.scales": "model.safetensors",
81
+ "acoustic_tokenizer.decoder.stages.0.4.ffn.linear2.weight": "model.safetensors",
82
+ "acoustic_tokenizer.decoder.stages.0.4.ffn_gamma": "model.safetensors",
83
+ "acoustic_tokenizer.decoder.stages.0.4.ffn_norm.weight": "model.safetensors",
84
+ "acoustic_tokenizer.decoder.stages.0.4.gamma": "model.safetensors",
85
+ "acoustic_tokenizer.decoder.stages.0.4.mixer.conv.conv.conv.bias": "model.safetensors",
86
+ "acoustic_tokenizer.decoder.stages.0.4.mixer.conv.conv.conv.weight": "model.safetensors",
87
+ "acoustic_tokenizer.decoder.stages.0.4.norm.weight": "model.safetensors",
88
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear1.bias": "model.safetensors",
89
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear1.biases": "model.safetensors",
90
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear1.scales": "model.safetensors",
91
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear1.weight": "model.safetensors",
92
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear2.bias": "model.safetensors",
93
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear2.biases": "model.safetensors",
94
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear2.scales": "model.safetensors",
95
+ "acoustic_tokenizer.decoder.stages.0.5.ffn.linear2.weight": "model.safetensors",
96
+ "acoustic_tokenizer.decoder.stages.0.5.ffn_gamma": "model.safetensors",
97
+ "acoustic_tokenizer.decoder.stages.0.5.ffn_norm.weight": "model.safetensors",
98
+ "acoustic_tokenizer.decoder.stages.0.5.gamma": "model.safetensors",
99
+ "acoustic_tokenizer.decoder.stages.0.5.mixer.conv.conv.conv.bias": "model.safetensors",
100
+ "acoustic_tokenizer.decoder.stages.0.5.mixer.conv.conv.conv.weight": "model.safetensors",
101
+ "acoustic_tokenizer.decoder.stages.0.5.norm.weight": "model.safetensors",
102
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear1.bias": "model.safetensors",
103
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear1.biases": "model.safetensors",
104
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear1.scales": "model.safetensors",
105
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear1.weight": "model.safetensors",
106
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear2.bias": "model.safetensors",
107
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear2.biases": "model.safetensors",
108
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear2.scales": "model.safetensors",
109
+ "acoustic_tokenizer.decoder.stages.0.6.ffn.linear2.weight": "model.safetensors",
110
+ "acoustic_tokenizer.decoder.stages.0.6.ffn_gamma": "model.safetensors",
111
+ "acoustic_tokenizer.decoder.stages.0.6.ffn_norm.weight": "model.safetensors",
112
+ "acoustic_tokenizer.decoder.stages.0.6.gamma": "model.safetensors",
113
+ "acoustic_tokenizer.decoder.stages.0.6.mixer.conv.conv.conv.bias": "model.safetensors",
114
+ "acoustic_tokenizer.decoder.stages.0.6.mixer.conv.conv.conv.weight": "model.safetensors",
115
+ "acoustic_tokenizer.decoder.stages.0.6.norm.weight": "model.safetensors",
116
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear1.bias": "model.safetensors",
117
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear1.biases": "model.safetensors",
118
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear1.scales": "model.safetensors",
119
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear1.weight": "model.safetensors",
120
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear2.bias": "model.safetensors",
121
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear2.biases": "model.safetensors",
122
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear2.scales": "model.safetensors",
123
+ "acoustic_tokenizer.decoder.stages.0.7.ffn.linear2.weight": "model.safetensors",
124
+ "acoustic_tokenizer.decoder.stages.0.7.ffn_gamma": "model.safetensors",
125
+ "acoustic_tokenizer.decoder.stages.0.7.ffn_norm.weight": "model.safetensors",
126
+ "acoustic_tokenizer.decoder.stages.0.7.gamma": "model.safetensors",
127
+ "acoustic_tokenizer.decoder.stages.0.7.mixer.conv.conv.conv.bias": "model.safetensors",
128
+ "acoustic_tokenizer.decoder.stages.0.7.mixer.conv.conv.conv.weight": "model.safetensors",
129
+ "acoustic_tokenizer.decoder.stages.0.7.norm.weight": "model.safetensors",
130
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear1.bias": "model.safetensors",
131
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear1.biases": "model.safetensors",
132
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear1.scales": "model.safetensors",
133
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear1.weight": "model.safetensors",
134
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear2.bias": "model.safetensors",
135
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear2.biases": "model.safetensors",
136
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear2.scales": "model.safetensors",
137
+ "acoustic_tokenizer.decoder.stages.1.0.ffn.linear2.weight": "model.safetensors",
138
+ "acoustic_tokenizer.decoder.stages.1.0.ffn_gamma": "model.safetensors",
139
+ "acoustic_tokenizer.decoder.stages.1.0.ffn_norm.weight": "model.safetensors",
140
+ "acoustic_tokenizer.decoder.stages.1.0.gamma": "model.safetensors",
141
+ "acoustic_tokenizer.decoder.stages.1.0.mixer.conv.conv.conv.bias": "model.safetensors",
142
+ "acoustic_tokenizer.decoder.stages.1.0.mixer.conv.conv.conv.weight": "model.safetensors",
143
+ "acoustic_tokenizer.decoder.stages.1.0.norm.weight": "model.safetensors",
144
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear1.bias": "model.safetensors",
145
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear1.biases": "model.safetensors",
146
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear1.scales": "model.safetensors",
147
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear1.weight": "model.safetensors",
148
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear2.bias": "model.safetensors",
149
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear2.biases": "model.safetensors",
150
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear2.scales": "model.safetensors",
151
+ "acoustic_tokenizer.decoder.stages.1.1.ffn.linear2.weight": "model.safetensors",
152
+ "acoustic_tokenizer.decoder.stages.1.1.ffn_gamma": "model.safetensors",
153
+ "acoustic_tokenizer.decoder.stages.1.1.ffn_norm.weight": "model.safetensors",
154
+ "acoustic_tokenizer.decoder.stages.1.1.gamma": "model.safetensors",
155
+ "acoustic_tokenizer.decoder.stages.1.1.mixer.conv.conv.conv.bias": "model.safetensors",
156
+ "acoustic_tokenizer.decoder.stages.1.1.mixer.conv.conv.conv.weight": "model.safetensors",
157
+ "acoustic_tokenizer.decoder.stages.1.1.norm.weight": "model.safetensors",
158
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear1.bias": "model.safetensors",
159
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear1.biases": "model.safetensors",
160
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear1.scales": "model.safetensors",
161
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear1.weight": "model.safetensors",
162
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear2.bias": "model.safetensors",
163
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear2.biases": "model.safetensors",
164
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear2.scales": "model.safetensors",
165
+ "acoustic_tokenizer.decoder.stages.1.2.ffn.linear2.weight": "model.safetensors",
166
+ "acoustic_tokenizer.decoder.stages.1.2.ffn_gamma": "model.safetensors",
167
+ "acoustic_tokenizer.decoder.stages.1.2.ffn_norm.weight": "model.safetensors",
168
+ "acoustic_tokenizer.decoder.stages.1.2.gamma": "model.safetensors",
169
+ "acoustic_tokenizer.decoder.stages.1.2.mixer.conv.conv.conv.bias": "model.safetensors",
170
+ "acoustic_tokenizer.decoder.stages.1.2.mixer.conv.conv.conv.weight": "model.safetensors",
171
+ "acoustic_tokenizer.decoder.stages.1.2.norm.weight": "model.safetensors",
172
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear1.bias": "model.safetensors",
173
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear1.biases": "model.safetensors",
174
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear1.scales": "model.safetensors",
175
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear1.weight": "model.safetensors",
176
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear2.bias": "model.safetensors",
177
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear2.biases": "model.safetensors",
178
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear2.scales": "model.safetensors",
179
+ "acoustic_tokenizer.decoder.stages.2.0.ffn.linear2.weight": "model.safetensors",
180
+ "acoustic_tokenizer.decoder.stages.2.0.ffn_gamma": "model.safetensors",
181
+ "acoustic_tokenizer.decoder.stages.2.0.ffn_norm.weight": "model.safetensors",
182
+ "acoustic_tokenizer.decoder.stages.2.0.gamma": "model.safetensors",
183
+ "acoustic_tokenizer.decoder.stages.2.0.mixer.conv.conv.conv.bias": "model.safetensors",
184
+ "acoustic_tokenizer.decoder.stages.2.0.mixer.conv.conv.conv.weight": "model.safetensors",
185
+ "acoustic_tokenizer.decoder.stages.2.0.norm.weight": "model.safetensors",
186
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear1.bias": "model.safetensors",
187
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear1.biases": "model.safetensors",
188
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear1.scales": "model.safetensors",
189
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear1.weight": "model.safetensors",
190
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear2.bias": "model.safetensors",
191
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear2.biases": "model.safetensors",
192
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear2.scales": "model.safetensors",
193
+ "acoustic_tokenizer.decoder.stages.2.1.ffn.linear2.weight": "model.safetensors",
194
+ "acoustic_tokenizer.decoder.stages.2.1.ffn_gamma": "model.safetensors",
195
+ "acoustic_tokenizer.decoder.stages.2.1.ffn_norm.weight": "model.safetensors",
196
+ "acoustic_tokenizer.decoder.stages.2.1.gamma": "model.safetensors",
197
+ "acoustic_tokenizer.decoder.stages.2.1.mixer.conv.conv.conv.bias": "model.safetensors",
198
+ "acoustic_tokenizer.decoder.stages.2.1.mixer.conv.conv.conv.weight": "model.safetensors",
199
+ "acoustic_tokenizer.decoder.stages.2.1.norm.weight": "model.safetensors",
200
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear1.bias": "model.safetensors",
201
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear1.biases": "model.safetensors",
202
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear1.scales": "model.safetensors",
203
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear1.weight": "model.safetensors",
204
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear2.bias": "model.safetensors",
205
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear2.biases": "model.safetensors",
206
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear2.scales": "model.safetensors",
207
+ "acoustic_tokenizer.decoder.stages.2.2.ffn.linear2.weight": "model.safetensors",
208
+ "acoustic_tokenizer.decoder.stages.2.2.ffn_gamma": "model.safetensors",
209
+ "acoustic_tokenizer.decoder.stages.2.2.ffn_norm.weight": "model.safetensors",
210
+ "acoustic_tokenizer.decoder.stages.2.2.gamma": "model.safetensors",
211
+ "acoustic_tokenizer.decoder.stages.2.2.mixer.conv.conv.conv.bias": "model.safetensors",
212
+ "acoustic_tokenizer.decoder.stages.2.2.mixer.conv.conv.conv.weight": "model.safetensors",
213
+ "acoustic_tokenizer.decoder.stages.2.2.norm.weight": "model.safetensors",
214
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear1.bias": "model.safetensors",
215
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear1.biases": "model.safetensors",
216
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear1.scales": "model.safetensors",
217
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear1.weight": "model.safetensors",
218
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear2.bias": "model.safetensors",
219
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear2.biases": "model.safetensors",
220
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear2.scales": "model.safetensors",
221
+ "acoustic_tokenizer.decoder.stages.3.0.ffn.linear2.weight": "model.safetensors",
222
+ "acoustic_tokenizer.decoder.stages.3.0.ffn_gamma": "model.safetensors",
223
+ "acoustic_tokenizer.decoder.stages.3.0.ffn_norm.weight": "model.safetensors",
224
+ "acoustic_tokenizer.decoder.stages.3.0.gamma": "model.safetensors",
225
+ "acoustic_tokenizer.decoder.stages.3.0.mixer.conv.conv.conv.bias": "model.safetensors",
226
+ "acoustic_tokenizer.decoder.stages.3.0.mixer.conv.conv.conv.weight": "model.safetensors",
227
+ "acoustic_tokenizer.decoder.stages.3.0.norm.weight": "model.safetensors",
228
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear1.bias": "model.safetensors",
229
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear1.biases": "model.safetensors",
230
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear1.scales": "model.safetensors",
231
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear1.weight": "model.safetensors",
232
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear2.bias": "model.safetensors",
233
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear2.biases": "model.safetensors",
234
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear2.scales": "model.safetensors",
235
+ "acoustic_tokenizer.decoder.stages.3.1.ffn.linear2.weight": "model.safetensors",
236
+ "acoustic_tokenizer.decoder.stages.3.1.ffn_gamma": "model.safetensors",
237
+ "acoustic_tokenizer.decoder.stages.3.1.ffn_norm.weight": "model.safetensors",
238
+ "acoustic_tokenizer.decoder.stages.3.1.gamma": "model.safetensors",
239
+ "acoustic_tokenizer.decoder.stages.3.1.mixer.conv.conv.conv.bias": "model.safetensors",
240
+ "acoustic_tokenizer.decoder.stages.3.1.mixer.conv.conv.conv.weight": "model.safetensors",
241
+ "acoustic_tokenizer.decoder.stages.3.1.norm.weight": "model.safetensors",
242
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear1.bias": "model.safetensors",
243
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear1.biases": "model.safetensors",
244
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear1.scales": "model.safetensors",
245
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear1.weight": "model.safetensors",
246
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear2.bias": "model.safetensors",
247
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear2.biases": "model.safetensors",
248
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear2.scales": "model.safetensors",
249
+ "acoustic_tokenizer.decoder.stages.3.2.ffn.linear2.weight": "model.safetensors",
250
+ "acoustic_tokenizer.decoder.stages.3.2.ffn_gamma": "model.safetensors",
251
+ "acoustic_tokenizer.decoder.stages.3.2.ffn_norm.weight": "model.safetensors",
252
+ "acoustic_tokenizer.decoder.stages.3.2.gamma": "model.safetensors",
253
+ "acoustic_tokenizer.decoder.stages.3.2.mixer.conv.conv.conv.bias": "model.safetensors",
254
+ "acoustic_tokenizer.decoder.stages.3.2.mixer.conv.conv.conv.weight": "model.safetensors",
255
+ "acoustic_tokenizer.decoder.stages.3.2.norm.weight": "model.safetensors",
256
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear1.bias": "model.safetensors",
257
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear1.biases": "model.safetensors",
258
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear1.scales": "model.safetensors",
259
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear1.weight": "model.safetensors",
260
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear2.bias": "model.safetensors",
261
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear2.biases": "model.safetensors",
262
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear2.scales": "model.safetensors",
263
+ "acoustic_tokenizer.decoder.stages.4.0.ffn.linear2.weight": "model.safetensors",
264
+ "acoustic_tokenizer.decoder.stages.4.0.ffn_gamma": "model.safetensors",
265
+ "acoustic_tokenizer.decoder.stages.4.0.ffn_norm.weight": "model.safetensors",
266
+ "acoustic_tokenizer.decoder.stages.4.0.gamma": "model.safetensors",
267
+ "acoustic_tokenizer.decoder.stages.4.0.mixer.conv.conv.conv.bias": "model.safetensors",
268
+ "acoustic_tokenizer.decoder.stages.4.0.mixer.conv.conv.conv.weight": "model.safetensors",
269
+ "acoustic_tokenizer.decoder.stages.4.0.norm.weight": "model.safetensors",
270
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear1.bias": "model.safetensors",
271
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear1.biases": "model.safetensors",
272
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear1.scales": "model.safetensors",
273
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear1.weight": "model.safetensors",
274
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear2.bias": "model.safetensors",
275
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear2.biases": "model.safetensors",
276
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear2.scales": "model.safetensors",
277
+ "acoustic_tokenizer.decoder.stages.4.1.ffn.linear2.weight": "model.safetensors",
278
+ "acoustic_tokenizer.decoder.stages.4.1.ffn_gamma": "model.safetensors",
279
+ "acoustic_tokenizer.decoder.stages.4.1.ffn_norm.weight": "model.safetensors",
280
+ "acoustic_tokenizer.decoder.stages.4.1.gamma": "model.safetensors",
281
+ "acoustic_tokenizer.decoder.stages.4.1.mixer.conv.conv.conv.bias": "model.safetensors",
282
+ "acoustic_tokenizer.decoder.stages.4.1.mixer.conv.conv.conv.weight": "model.safetensors",
283
+ "acoustic_tokenizer.decoder.stages.4.1.norm.weight": "model.safetensors",
284
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear1.bias": "model.safetensors",
285
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear1.biases": "model.safetensors",
286
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear1.scales": "model.safetensors",
287
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear1.weight": "model.safetensors",
288
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear2.bias": "model.safetensors",
289
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear2.biases": "model.safetensors",
290
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear2.scales": "model.safetensors",
291
+ "acoustic_tokenizer.decoder.stages.4.2.ffn.linear2.weight": "model.safetensors",
292
+ "acoustic_tokenizer.decoder.stages.4.2.ffn_gamma": "model.safetensors",
293
+ "acoustic_tokenizer.decoder.stages.4.2.ffn_norm.weight": "model.safetensors",
294
+ "acoustic_tokenizer.decoder.stages.4.2.gamma": "model.safetensors",
295
+ "acoustic_tokenizer.decoder.stages.4.2.mixer.conv.conv.conv.bias": "model.safetensors",
296
+ "acoustic_tokenizer.decoder.stages.4.2.mixer.conv.conv.conv.weight": "model.safetensors",
297
+ "acoustic_tokenizer.decoder.stages.4.2.norm.weight": "model.safetensors",
298
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear1.bias": "model.safetensors",
299
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear1.biases": "model.safetensors",
300
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear1.scales": "model.safetensors",
301
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear1.weight": "model.safetensors",
302
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear2.bias": "model.safetensors",
303
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear2.biases": "model.safetensors",
304
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear2.scales": "model.safetensors",
305
+ "acoustic_tokenizer.decoder.stages.5.0.ffn.linear2.weight": "model.safetensors",
306
+ "acoustic_tokenizer.decoder.stages.5.0.ffn_gamma": "model.safetensors",
307
+ "acoustic_tokenizer.decoder.stages.5.0.ffn_norm.weight": "model.safetensors",
308
+ "acoustic_tokenizer.decoder.stages.5.0.gamma": "model.safetensors",
309
+ "acoustic_tokenizer.decoder.stages.5.0.mixer.conv.conv.conv.bias": "model.safetensors",
310
+ "acoustic_tokenizer.decoder.stages.5.0.mixer.conv.conv.conv.weight": "model.safetensors",
311
+ "acoustic_tokenizer.decoder.stages.5.0.norm.weight": "model.safetensors",
312
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear1.bias": "model.safetensors",
313
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear1.biases": "model.safetensors",
314
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear1.scales": "model.safetensors",
315
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear1.weight": "model.safetensors",
316
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear2.bias": "model.safetensors",
317
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear2.biases": "model.safetensors",
318
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear2.scales": "model.safetensors",
319
+ "acoustic_tokenizer.decoder.stages.5.1.ffn.linear2.weight": "model.safetensors",
320
+ "acoustic_tokenizer.decoder.stages.5.1.ffn_gamma": "model.safetensors",
321
+ "acoustic_tokenizer.decoder.stages.5.1.ffn_norm.weight": "model.safetensors",
322
+ "acoustic_tokenizer.decoder.stages.5.1.gamma": "model.safetensors",
323
+ "acoustic_tokenizer.decoder.stages.5.1.mixer.conv.conv.conv.bias": "model.safetensors",
324
+ "acoustic_tokenizer.decoder.stages.5.1.mixer.conv.conv.conv.weight": "model.safetensors",
325
+ "acoustic_tokenizer.decoder.stages.5.1.norm.weight": "model.safetensors",
326
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear1.bias": "model.safetensors",
327
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear1.biases": "model.safetensors",
328
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear1.scales": "model.safetensors",
329
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear1.weight": "model.safetensors",
330
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear2.bias": "model.safetensors",
331
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear2.biases": "model.safetensors",
332
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear2.scales": "model.safetensors",
333
+ "acoustic_tokenizer.decoder.stages.5.2.ffn.linear2.weight": "model.safetensors",
334
+ "acoustic_tokenizer.decoder.stages.5.2.ffn_gamma": "model.safetensors",
335
+ "acoustic_tokenizer.decoder.stages.5.2.ffn_norm.weight": "model.safetensors",
336
+ "acoustic_tokenizer.decoder.stages.5.2.gamma": "model.safetensors",
337
+ "acoustic_tokenizer.decoder.stages.5.2.mixer.conv.conv.conv.bias": "model.safetensors",
338
+ "acoustic_tokenizer.decoder.stages.5.2.mixer.conv.conv.conv.weight": "model.safetensors",
339
+ "acoustic_tokenizer.decoder.stages.5.2.norm.weight": "model.safetensors",
340
+ "acoustic_tokenizer.decoder.stages.6.0.ffn.linear1.bias": "model.safetensors",
341
+ "acoustic_tokenizer.decoder.stages.6.0.ffn.linear1.weight": "model.safetensors",
342
+ "acoustic_tokenizer.decoder.stages.6.0.ffn.linear2.bias": "model.safetensors",
343
+ "acoustic_tokenizer.decoder.stages.6.0.ffn.linear2.biases": "model.safetensors",
344
+ "acoustic_tokenizer.decoder.stages.6.0.ffn.linear2.scales": "model.safetensors",
345
+ "acoustic_tokenizer.decoder.stages.6.0.ffn.linear2.weight": "model.safetensors",
346
+ "acoustic_tokenizer.decoder.stages.6.0.ffn_gamma": "model.safetensors",
347
+ "acoustic_tokenizer.decoder.stages.6.0.ffn_norm.weight": "model.safetensors",
348
+ "acoustic_tokenizer.decoder.stages.6.0.gamma": "model.safetensors",
349
+ "acoustic_tokenizer.decoder.stages.6.0.mixer.conv.conv.conv.bias": "model.safetensors",
350
+ "acoustic_tokenizer.decoder.stages.6.0.mixer.conv.conv.conv.weight": "model.safetensors",
351
+ "acoustic_tokenizer.decoder.stages.6.0.norm.weight": "model.safetensors",
352
+ "acoustic_tokenizer.decoder.stages.6.1.ffn.linear1.bias": "model.safetensors",
353
+ "acoustic_tokenizer.decoder.stages.6.1.ffn.linear1.weight": "model.safetensors",
354
+ "acoustic_tokenizer.decoder.stages.6.1.ffn.linear2.bias": "model.safetensors",
355
+ "acoustic_tokenizer.decoder.stages.6.1.ffn.linear2.biases": "model.safetensors",
356
+ "acoustic_tokenizer.decoder.stages.6.1.ffn.linear2.scales": "model.safetensors",
357
+ "acoustic_tokenizer.decoder.stages.6.1.ffn.linear2.weight": "model.safetensors",
358
+ "acoustic_tokenizer.decoder.stages.6.1.ffn_gamma": "model.safetensors",
359
+ "acoustic_tokenizer.decoder.stages.6.1.ffn_norm.weight": "model.safetensors",
360
+ "acoustic_tokenizer.decoder.stages.6.1.gamma": "model.safetensors",
361
+ "acoustic_tokenizer.decoder.stages.6.1.mixer.conv.conv.conv.bias": "model.safetensors",
362
+ "acoustic_tokenizer.decoder.stages.6.1.mixer.conv.conv.conv.weight": "model.safetensors",
363
+ "acoustic_tokenizer.decoder.stages.6.1.norm.weight": "model.safetensors",
364
+ "acoustic_tokenizer.decoder.stages.6.2.ffn.linear1.bias": "model.safetensors",
365
+ "acoustic_tokenizer.decoder.stages.6.2.ffn.linear1.weight": "model.safetensors",
366
+ "acoustic_tokenizer.decoder.stages.6.2.ffn.linear2.bias": "model.safetensors",
367
+ "acoustic_tokenizer.decoder.stages.6.2.ffn.linear2.biases": "model.safetensors",
368
+ "acoustic_tokenizer.decoder.stages.6.2.ffn.linear2.scales": "model.safetensors",
369
+ "acoustic_tokenizer.decoder.stages.6.2.ffn.linear2.weight": "model.safetensors",
370
+ "acoustic_tokenizer.decoder.stages.6.2.ffn_gamma": "model.safetensors",
371
+ "acoustic_tokenizer.decoder.stages.6.2.ffn_norm.weight": "model.safetensors",
372
+ "acoustic_tokenizer.decoder.stages.6.2.gamma": "model.safetensors",
373
+ "acoustic_tokenizer.decoder.stages.6.2.mixer.conv.conv.conv.bias": "model.safetensors",
374
+ "acoustic_tokenizer.decoder.stages.6.2.mixer.conv.conv.conv.weight": "model.safetensors",
375
+ "acoustic_tokenizer.decoder.stages.6.2.norm.weight": "model.safetensors",
376
+ "acoustic_tokenizer.decoder.upsample_layers.0.0.conv.conv.bias": "model.safetensors",
377
+ "acoustic_tokenizer.decoder.upsample_layers.0.0.conv.conv.weight": "model.safetensors",
378
+ "acoustic_tokenizer.decoder.upsample_layers.1.0.convtr.convtr.bias": "model.safetensors",
379
+ "acoustic_tokenizer.decoder.upsample_layers.1.0.convtr.convtr.weight": "model.safetensors",
380
+ "acoustic_tokenizer.decoder.upsample_layers.2.0.convtr.convtr.bias": "model.safetensors",
381
+ "acoustic_tokenizer.decoder.upsample_layers.2.0.convtr.convtr.weight": "model.safetensors",
382
+ "acoustic_tokenizer.decoder.upsample_layers.3.0.convtr.convtr.bias": "model.safetensors",
383
+ "acoustic_tokenizer.decoder.upsample_layers.3.0.convtr.convtr.weight": "model.safetensors",
384
+ "acoustic_tokenizer.decoder.upsample_layers.4.0.convtr.convtr.bias": "model.safetensors",
385
+ "acoustic_tokenizer.decoder.upsample_layers.4.0.convtr.convtr.weight": "model.safetensors",
386
+ "acoustic_tokenizer.decoder.upsample_layers.5.0.convtr.convtr.bias": "model.safetensors",
387
+ "acoustic_tokenizer.decoder.upsample_layers.5.0.convtr.convtr.weight": "model.safetensors",
388
+ "acoustic_tokenizer.decoder.upsample_layers.6.0.convtr.convtr.bias": "model.safetensors",
389
+ "acoustic_tokenizer.decoder.upsample_layers.6.0.convtr.convtr.weight": "model.safetensors",
390
+ "language_model.embed_tokens.biases": "model.safetensors",
391
+ "language_model.embed_tokens.scales": "model.safetensors",
392
+ "language_model.embed_tokens.weight": "model.safetensors",
393
+ "language_model.layers.0.input_layernorm.weight": "model.safetensors",
394
+ "language_model.layers.0.mlp.down_proj.biases": "model.safetensors",
395
+ "language_model.layers.0.mlp.down_proj.scales": "model.safetensors",
396
+ "language_model.layers.0.mlp.down_proj.weight": "model.safetensors",
397
+ "language_model.layers.0.mlp.gate_proj.biases": "model.safetensors",
398
+ "language_model.layers.0.mlp.gate_proj.scales": "model.safetensors",
399
+ "language_model.layers.0.mlp.gate_proj.weight": "model.safetensors",
400
+ "language_model.layers.0.mlp.up_proj.biases": "model.safetensors",
401
+ "language_model.layers.0.mlp.up_proj.scales": "model.safetensors",
402
+ "language_model.layers.0.mlp.up_proj.weight": "model.safetensors",
403
+ "language_model.layers.0.post_attention_layernorm.weight": "model.safetensors",
404
+ "language_model.layers.0.self_attn.k_proj.bias": "model.safetensors",
405
+ "language_model.layers.0.self_attn.k_proj.biases": "model.safetensors",
406
+ "language_model.layers.0.self_attn.k_proj.scales": "model.safetensors",
407
+ "language_model.layers.0.self_attn.k_proj.weight": "model.safetensors",
408
+ "language_model.layers.0.self_attn.o_proj.biases": "model.safetensors",
409
+ "language_model.layers.0.self_attn.o_proj.scales": "model.safetensors",
410
+ "language_model.layers.0.self_attn.o_proj.weight": "model.safetensors",
411
+ "language_model.layers.0.self_attn.q_proj.bias": "model.safetensors",
412
+ "language_model.layers.0.self_attn.q_proj.biases": "model.safetensors",
413
+ "language_model.layers.0.self_attn.q_proj.scales": "model.safetensors",
414
+ "language_model.layers.0.self_attn.q_proj.weight": "model.safetensors",
415
+ "language_model.layers.0.self_attn.v_proj.bias": "model.safetensors",
416
+ "language_model.layers.0.self_attn.v_proj.biases": "model.safetensors",
417
+ "language_model.layers.0.self_attn.v_proj.scales": "model.safetensors",
418
+ "language_model.layers.0.self_attn.v_proj.weight": "model.safetensors",
419
+ "language_model.layers.1.input_layernorm.weight": "model.safetensors",
420
+ "language_model.layers.1.mlp.down_proj.biases": "model.safetensors",
421
+ "language_model.layers.1.mlp.down_proj.scales": "model.safetensors",
422
+ "language_model.layers.1.mlp.down_proj.weight": "model.safetensors",
423
+ "language_model.layers.1.mlp.gate_proj.biases": "model.safetensors",
424
+ "language_model.layers.1.mlp.gate_proj.scales": "model.safetensors",
425
+ "language_model.layers.1.mlp.gate_proj.weight": "model.safetensors",
426
+ "language_model.layers.1.mlp.up_proj.biases": "model.safetensors",
427
+ "language_model.layers.1.mlp.up_proj.scales": "model.safetensors",
428
+ "language_model.layers.1.mlp.up_proj.weight": "model.safetensors",
429
+ "language_model.layers.1.post_attention_layernorm.weight": "model.safetensors",
430
+ "language_model.layers.1.self_attn.k_proj.bias": "model.safetensors",
431
+ "language_model.layers.1.self_attn.k_proj.biases": "model.safetensors",
432
+ "language_model.layers.1.self_attn.k_proj.scales": "model.safetensors",
433
+ "language_model.layers.1.self_attn.k_proj.weight": "model.safetensors",
434
+ "language_model.layers.1.self_attn.o_proj.biases": "model.safetensors",
435
+ "language_model.layers.1.self_attn.o_proj.scales": "model.safetensors",
436
+ "language_model.layers.1.self_attn.o_proj.weight": "model.safetensors",
437
+ "language_model.layers.1.self_attn.q_proj.bias": "model.safetensors",
438
+ "language_model.layers.1.self_attn.q_proj.biases": "model.safetensors",
439
+ "language_model.layers.1.self_attn.q_proj.scales": "model.safetensors",
440
+ "language_model.layers.1.self_attn.q_proj.weight": "model.safetensors",
441
+ "language_model.layers.1.self_attn.v_proj.bias": "model.safetensors",
442
+ "language_model.layers.1.self_attn.v_proj.biases": "model.safetensors",
443
+ "language_model.layers.1.self_attn.v_proj.scales": "model.safetensors",
444
+ "language_model.layers.1.self_attn.v_proj.weight": "model.safetensors",
445
+ "language_model.layers.2.input_layernorm.weight": "model.safetensors",
446
+ "language_model.layers.2.mlp.down_proj.biases": "model.safetensors",
447
+ "language_model.layers.2.mlp.down_proj.scales": "model.safetensors",
448
+ "language_model.layers.2.mlp.down_proj.weight": "model.safetensors",
449
+ "language_model.layers.2.mlp.gate_proj.biases": "model.safetensors",
450
+ "language_model.layers.2.mlp.gate_proj.scales": "model.safetensors",
451
+ "language_model.layers.2.mlp.gate_proj.weight": "model.safetensors",
452
+ "language_model.layers.2.mlp.up_proj.biases": "model.safetensors",
453
+ "language_model.layers.2.mlp.up_proj.scales": "model.safetensors",
454
+ "language_model.layers.2.mlp.up_proj.weight": "model.safetensors",
455
+ "language_model.layers.2.post_attention_layernorm.weight": "model.safetensors",
456
+ "language_model.layers.2.self_attn.k_proj.bias": "model.safetensors",
457
+ "language_model.layers.2.self_attn.k_proj.biases": "model.safetensors",
458
+ "language_model.layers.2.self_attn.k_proj.scales": "model.safetensors",
459
+ "language_model.layers.2.self_attn.k_proj.weight": "model.safetensors",
460
+ "language_model.layers.2.self_attn.o_proj.biases": "model.safetensors",
461
+ "language_model.layers.2.self_attn.o_proj.scales": "model.safetensors",
462
+ "language_model.layers.2.self_attn.o_proj.weight": "model.safetensors",
463
+ "language_model.layers.2.self_attn.q_proj.bias": "model.safetensors",
464
+ "language_model.layers.2.self_attn.q_proj.biases": "model.safetensors",
465
+ "language_model.layers.2.self_attn.q_proj.scales": "model.safetensors",
466
+ "language_model.layers.2.self_attn.q_proj.weight": "model.safetensors",
467
+ "language_model.layers.2.self_attn.v_proj.bias": "model.safetensors",
468
+ "language_model.layers.2.self_attn.v_proj.biases": "model.safetensors",
469
+ "language_model.layers.2.self_attn.v_proj.scales": "model.safetensors",
470
+ "language_model.layers.2.self_attn.v_proj.weight": "model.safetensors",
471
+ "language_model.layers.3.input_layernorm.weight": "model.safetensors",
472
+ "language_model.layers.3.mlp.down_proj.biases": "model.safetensors",
473
+ "language_model.layers.3.mlp.down_proj.scales": "model.safetensors",
474
+ "language_model.layers.3.mlp.down_proj.weight": "model.safetensors",
475
+ "language_model.layers.3.mlp.gate_proj.biases": "model.safetensors",
476
+ "language_model.layers.3.mlp.gate_proj.scales": "model.safetensors",
477
+ "language_model.layers.3.mlp.gate_proj.weight": "model.safetensors",
478
+ "language_model.layers.3.mlp.up_proj.biases": "model.safetensors",
479
+ "language_model.layers.3.mlp.up_proj.scales": "model.safetensors",
480
+ "language_model.layers.3.mlp.up_proj.weight": "model.safetensors",
481
+ "language_model.layers.3.post_attention_layernorm.weight": "model.safetensors",
482
+ "language_model.layers.3.self_attn.k_proj.bias": "model.safetensors",
483
+ "language_model.layers.3.self_attn.k_proj.biases": "model.safetensors",
484
+ "language_model.layers.3.self_attn.k_proj.scales": "model.safetensors",
485
+ "language_model.layers.3.self_attn.k_proj.weight": "model.safetensors",
486
+ "language_model.layers.3.self_attn.o_proj.biases": "model.safetensors",
487
+ "language_model.layers.3.self_attn.o_proj.scales": "model.safetensors",
488
+ "language_model.layers.3.self_attn.o_proj.weight": "model.safetensors",
489
+ "language_model.layers.3.self_attn.q_proj.bias": "model.safetensors",
490
+ "language_model.layers.3.self_attn.q_proj.biases": "model.safetensors",
491
+ "language_model.layers.3.self_attn.q_proj.scales": "model.safetensors",
492
+ "language_model.layers.3.self_attn.q_proj.weight": "model.safetensors",
493
+ "language_model.layers.3.self_attn.v_proj.bias": "model.safetensors",
494
+ "language_model.layers.3.self_attn.v_proj.biases": "model.safetensors",
495
+ "language_model.layers.3.self_attn.v_proj.scales": "model.safetensors",
496
+ "language_model.layers.3.self_attn.v_proj.weight": "model.safetensors",
497
+ "prediction_head.cond_proj.biases": "model.safetensors",
498
+ "prediction_head.cond_proj.scales": "model.safetensors",
499
+ "prediction_head.cond_proj.weight": "model.safetensors",
500
+ "prediction_head.final_layer.adaLN_modulation.layers.1.biases": "model.safetensors",
501
+ "prediction_head.final_layer.adaLN_modulation.layers.1.scales": "model.safetensors",
502
+ "prediction_head.final_layer.adaLN_modulation.layers.1.weight": "model.safetensors",
503
+ "prediction_head.final_layer.linear.biases": "model.safetensors",
504
+ "prediction_head.final_layer.linear.scales": "model.safetensors",
505
+ "prediction_head.final_layer.linear.weight": "model.safetensors",
506
+ "prediction_head.layers.0.adaLN_modulation.layers.1.biases": "model.safetensors",
507
+ "prediction_head.layers.0.adaLN_modulation.layers.1.scales": "model.safetensors",
508
+ "prediction_head.layers.0.adaLN_modulation.layers.1.weight": "model.safetensors",
509
+ "prediction_head.layers.0.ffn.down_proj.biases": "model.safetensors",
510
+ "prediction_head.layers.0.ffn.down_proj.scales": "model.safetensors",
511
+ "prediction_head.layers.0.ffn.down_proj.weight": "model.safetensors",
512
+ "prediction_head.layers.0.ffn.gate_proj.biases": "model.safetensors",
513
+ "prediction_head.layers.0.ffn.gate_proj.scales": "model.safetensors",
514
+ "prediction_head.layers.0.ffn.gate_proj.weight": "model.safetensors",
515
+ "prediction_head.layers.0.ffn.up_proj.biases": "model.safetensors",
516
+ "prediction_head.layers.0.ffn.up_proj.scales": "model.safetensors",
517
+ "prediction_head.layers.0.ffn.up_proj.weight": "model.safetensors",
518
+ "prediction_head.layers.0.norm.weight": "model.safetensors",
519
+ "prediction_head.layers.1.adaLN_modulation.layers.1.biases": "model.safetensors",
520
+ "prediction_head.layers.1.adaLN_modulation.layers.1.scales": "model.safetensors",
521
+ "prediction_head.layers.1.adaLN_modulation.layers.1.weight": "model.safetensors",
522
+ "prediction_head.layers.1.ffn.down_proj.biases": "model.safetensors",
523
+ "prediction_head.layers.1.ffn.down_proj.scales": "model.safetensors",
524
+ "prediction_head.layers.1.ffn.down_proj.weight": "model.safetensors",
525
+ "prediction_head.layers.1.ffn.gate_proj.biases": "model.safetensors",
526
+ "prediction_head.layers.1.ffn.gate_proj.scales": "model.safetensors",
527
+ "prediction_head.layers.1.ffn.gate_proj.weight": "model.safetensors",
528
+ "prediction_head.layers.1.ffn.up_proj.biases": "model.safetensors",
529
+ "prediction_head.layers.1.ffn.up_proj.scales": "model.safetensors",
530
+ "prediction_head.layers.1.ffn.up_proj.weight": "model.safetensors",
531
+ "prediction_head.layers.1.norm.weight": "model.safetensors",
532
+ "prediction_head.layers.2.adaLN_modulation.layers.1.biases": "model.safetensors",
533
+ "prediction_head.layers.2.adaLN_modulation.layers.1.scales": "model.safetensors",
534
+ "prediction_head.layers.2.adaLN_modulation.layers.1.weight": "model.safetensors",
535
+ "prediction_head.layers.2.ffn.down_proj.biases": "model.safetensors",
536
+ "prediction_head.layers.2.ffn.down_proj.scales": "model.safetensors",
537
+ "prediction_head.layers.2.ffn.down_proj.weight": "model.safetensors",
538
+ "prediction_head.layers.2.ffn.gate_proj.biases": "model.safetensors",
539
+ "prediction_head.layers.2.ffn.gate_proj.scales": "model.safetensors",
540
+ "prediction_head.layers.2.ffn.gate_proj.weight": "model.safetensors",
541
+ "prediction_head.layers.2.ffn.up_proj.biases": "model.safetensors",
542
+ "prediction_head.layers.2.ffn.up_proj.scales": "model.safetensors",
543
+ "prediction_head.layers.2.ffn.up_proj.weight": "model.safetensors",
544
+ "prediction_head.layers.2.norm.weight": "model.safetensors",
545
+ "prediction_head.layers.3.adaLN_modulation.layers.1.biases": "model.safetensors",
546
+ "prediction_head.layers.3.adaLN_modulation.layers.1.scales": "model.safetensors",
547
+ "prediction_head.layers.3.adaLN_modulation.layers.1.weight": "model.safetensors",
548
+ "prediction_head.layers.3.ffn.down_proj.biases": "model.safetensors",
549
+ "prediction_head.layers.3.ffn.down_proj.scales": "model.safetensors",
550
+ "prediction_head.layers.3.ffn.down_proj.weight": "model.safetensors",
551
+ "prediction_head.layers.3.ffn.gate_proj.biases": "model.safetensors",
552
+ "prediction_head.layers.3.ffn.gate_proj.scales": "model.safetensors",
553
+ "prediction_head.layers.3.ffn.gate_proj.weight": "model.safetensors",
554
+ "prediction_head.layers.3.ffn.up_proj.biases": "model.safetensors",
555
+ "prediction_head.layers.3.ffn.up_proj.scales": "model.safetensors",
556
+ "prediction_head.layers.3.ffn.up_proj.weight": "model.safetensors",
557
+ "prediction_head.layers.3.norm.weight": "model.safetensors",
558
+ "prediction_head.noisy_images_proj.biases": "model.safetensors",
559
+ "prediction_head.noisy_images_proj.scales": "model.safetensors",
560
+ "prediction_head.noisy_images_proj.weight": "model.safetensors",
561
+ "prediction_head.t_embedder.mlp.layers.0.biases": "model.safetensors",
562
+ "prediction_head.t_embedder.mlp.layers.0.scales": "model.safetensors",
563
+ "prediction_head.t_embedder.mlp.layers.0.weight": "model.safetensors",
564
+ "prediction_head.t_embedder.mlp.layers.2.biases": "model.safetensors",
565
+ "prediction_head.t_embedder.mlp.layers.2.scales": "model.safetensors",
566
+ "prediction_head.t_embedder.mlp.layers.2.weight": "model.safetensors",
567
+ "speech_bias_factor": "model.safetensors",
568
+ "speech_scaling_factor": "model.safetensors",
569
+ "tts_eos_classifier.fc1.bias": "model.safetensors",
570
+ "tts_eos_classifier.fc1.biases": "model.safetensors",
571
+ "tts_eos_classifier.fc1.scales": "model.safetensors",
572
+ "tts_eos_classifier.fc1.weight": "model.safetensors",
573
+ "tts_eos_classifier.fc2.bias": "model.safetensors",
574
+ "tts_eos_classifier.fc2.biases": "model.safetensors",
575
+ "tts_eos_classifier.fc2.scales": "model.safetensors",
576
+ "tts_eos_classifier.fc2.weight": "model.safetensors",
577
+ "tts_input_types.biases": "model.safetensors",
578
+ "tts_input_types.scales": "model.safetensors",
579
+ "tts_input_types.weight": "model.safetensors",
580
+ "tts_language_model.embed_tokens.biases": "model.safetensors",
581
+ "tts_language_model.embed_tokens.scales": "model.safetensors",
582
+ "tts_language_model.embed_tokens.weight": "model.safetensors",
583
+ "tts_language_model.layers.0.input_layernorm.weight": "model.safetensors",
584
+ "tts_language_model.layers.0.mlp.down_proj.biases": "model.safetensors",
585
+ "tts_language_model.layers.0.mlp.down_proj.scales": "model.safetensors",
586
+ "tts_language_model.layers.0.mlp.down_proj.weight": "model.safetensors",
587
+ "tts_language_model.layers.0.mlp.gate_proj.biases": "model.safetensors",
588
+ "tts_language_model.layers.0.mlp.gate_proj.scales": "model.safetensors",
589
+ "tts_language_model.layers.0.mlp.gate_proj.weight": "model.safetensors",
590
+ "tts_language_model.layers.0.mlp.up_proj.biases": "model.safetensors",
591
+ "tts_language_model.layers.0.mlp.up_proj.scales": "model.safetensors",
592
+ "tts_language_model.layers.0.mlp.up_proj.weight": "model.safetensors",
593
+ "tts_language_model.layers.0.post_attention_layernorm.weight": "model.safetensors",
594
+ "tts_language_model.layers.0.self_attn.k_proj.bias": "model.safetensors",
595
+ "tts_language_model.layers.0.self_attn.k_proj.biases": "model.safetensors",
596
+ "tts_language_model.layers.0.self_attn.k_proj.scales": "model.safetensors",
597
+ "tts_language_model.layers.0.self_attn.k_proj.weight": "model.safetensors",
598
+ "tts_language_model.layers.0.self_attn.o_proj.biases": "model.safetensors",
599
+ "tts_language_model.layers.0.self_attn.o_proj.scales": "model.safetensors",
600
+ "tts_language_model.layers.0.self_attn.o_proj.weight": "model.safetensors",
601
+ "tts_language_model.layers.0.self_attn.q_proj.bias": "model.safetensors",
602
+ "tts_language_model.layers.0.self_attn.q_proj.biases": "model.safetensors",
603
+ "tts_language_model.layers.0.self_attn.q_proj.scales": "model.safetensors",
604
+ "tts_language_model.layers.0.self_attn.q_proj.weight": "model.safetensors",
605
+ "tts_language_model.layers.0.self_attn.v_proj.bias": "model.safetensors",
606
+ "tts_language_model.layers.0.self_attn.v_proj.biases": "model.safetensors",
607
+ "tts_language_model.layers.0.self_attn.v_proj.scales": "model.safetensors",
608
+ "tts_language_model.layers.0.self_attn.v_proj.weight": "model.safetensors",
609
+ "tts_language_model.layers.1.input_layernorm.weight": "model.safetensors",
610
+ "tts_language_model.layers.1.mlp.down_proj.biases": "model.safetensors",
611
+ "tts_language_model.layers.1.mlp.down_proj.scales": "model.safetensors",
612
+ "tts_language_model.layers.1.mlp.down_proj.weight": "model.safetensors",
613
+ "tts_language_model.layers.1.mlp.gate_proj.biases": "model.safetensors",
614
+ "tts_language_model.layers.1.mlp.gate_proj.scales": "model.safetensors",
615
+ "tts_language_model.layers.1.mlp.gate_proj.weight": "model.safetensors",
616
+ "tts_language_model.layers.1.mlp.up_proj.biases": "model.safetensors",
617
+ "tts_language_model.layers.1.mlp.up_proj.scales": "model.safetensors",
618
+ "tts_language_model.layers.1.mlp.up_proj.weight": "model.safetensors",
619
+ "tts_language_model.layers.1.post_attention_layernorm.weight": "model.safetensors",
620
+ "tts_language_model.layers.1.self_attn.k_proj.bias": "model.safetensors",
621
+ "tts_language_model.layers.1.self_attn.k_proj.biases": "model.safetensors",
622
+ "tts_language_model.layers.1.self_attn.k_proj.scales": "model.safetensors",
623
+ "tts_language_model.layers.1.self_attn.k_proj.weight": "model.safetensors",
624
+ "tts_language_model.layers.1.self_attn.o_proj.biases": "model.safetensors",
625
+ "tts_language_model.layers.1.self_attn.o_proj.scales": "model.safetensors",
626
+ "tts_language_model.layers.1.self_attn.o_proj.weight": "model.safetensors",
627
+ "tts_language_model.layers.1.self_attn.q_proj.bias": "model.safetensors",
628
+ "tts_language_model.layers.1.self_attn.q_proj.biases": "model.safetensors",
629
+ "tts_language_model.layers.1.self_attn.q_proj.scales": "model.safetensors",
630
+ "tts_language_model.layers.1.self_attn.q_proj.weight": "model.safetensors",
631
+ "tts_language_model.layers.1.self_attn.v_proj.bias": "model.safetensors",
632
+ "tts_language_model.layers.1.self_attn.v_proj.biases": "model.safetensors",
633
+ "tts_language_model.layers.1.self_attn.v_proj.scales": "model.safetensors",
634
+ "tts_language_model.layers.1.self_attn.v_proj.weight": "model.safetensors",
635
+ "tts_language_model.layers.10.input_layernorm.weight": "model.safetensors",
636
+ "tts_language_model.layers.10.mlp.down_proj.biases": "model.safetensors",
637
+ "tts_language_model.layers.10.mlp.down_proj.scales": "model.safetensors",
638
+ "tts_language_model.layers.10.mlp.down_proj.weight": "model.safetensors",
639
+ "tts_language_model.layers.10.mlp.gate_proj.biases": "model.safetensors",
640
+ "tts_language_model.layers.10.mlp.gate_proj.scales": "model.safetensors",
641
+ "tts_language_model.layers.10.mlp.gate_proj.weight": "model.safetensors",
642
+ "tts_language_model.layers.10.mlp.up_proj.biases": "model.safetensors",
643
+ "tts_language_model.layers.10.mlp.up_proj.scales": "model.safetensors",
644
+ "tts_language_model.layers.10.mlp.up_proj.weight": "model.safetensors",
645
+ "tts_language_model.layers.10.post_attention_layernorm.weight": "model.safetensors",
646
+ "tts_language_model.layers.10.self_attn.k_proj.bias": "model.safetensors",
647
+ "tts_language_model.layers.10.self_attn.k_proj.biases": "model.safetensors",
648
+ "tts_language_model.layers.10.self_attn.k_proj.scales": "model.safetensors",
649
+ "tts_language_model.layers.10.self_attn.k_proj.weight": "model.safetensors",
650
+ "tts_language_model.layers.10.self_attn.o_proj.biases": "model.safetensors",
651
+ "tts_language_model.layers.10.self_attn.o_proj.scales": "model.safetensors",
652
+ "tts_language_model.layers.10.self_attn.o_proj.weight": "model.safetensors",
653
+ "tts_language_model.layers.10.self_attn.q_proj.bias": "model.safetensors",
654
+ "tts_language_model.layers.10.self_attn.q_proj.biases": "model.safetensors",
655
+ "tts_language_model.layers.10.self_attn.q_proj.scales": "model.safetensors",
656
+ "tts_language_model.layers.10.self_attn.q_proj.weight": "model.safetensors",
657
+ "tts_language_model.layers.10.self_attn.v_proj.bias": "model.safetensors",
658
+ "tts_language_model.layers.10.self_attn.v_proj.biases": "model.safetensors",
659
+ "tts_language_model.layers.10.self_attn.v_proj.scales": "model.safetensors",
660
+ "tts_language_model.layers.10.self_attn.v_proj.weight": "model.safetensors",
661
+ "tts_language_model.layers.11.input_layernorm.weight": "model.safetensors",
662
+ "tts_language_model.layers.11.mlp.down_proj.biases": "model.safetensors",
663
+ "tts_language_model.layers.11.mlp.down_proj.scales": "model.safetensors",
664
+ "tts_language_model.layers.11.mlp.down_proj.weight": "model.safetensors",
665
+ "tts_language_model.layers.11.mlp.gate_proj.biases": "model.safetensors",
666
+ "tts_language_model.layers.11.mlp.gate_proj.scales": "model.safetensors",
667
+ "tts_language_model.layers.11.mlp.gate_proj.weight": "model.safetensors",
668
+ "tts_language_model.layers.11.mlp.up_proj.biases": "model.safetensors",
669
+ "tts_language_model.layers.11.mlp.up_proj.scales": "model.safetensors",
670
+ "tts_language_model.layers.11.mlp.up_proj.weight": "model.safetensors",
671
+ "tts_language_model.layers.11.post_attention_layernorm.weight": "model.safetensors",
672
+ "tts_language_model.layers.11.self_attn.k_proj.bias": "model.safetensors",
673
+ "tts_language_model.layers.11.self_attn.k_proj.biases": "model.safetensors",
674
+ "tts_language_model.layers.11.self_attn.k_proj.scales": "model.safetensors",
675
+ "tts_language_model.layers.11.self_attn.k_proj.weight": "model.safetensors",
676
+ "tts_language_model.layers.11.self_attn.o_proj.biases": "model.safetensors",
677
+ "tts_language_model.layers.11.self_attn.o_proj.scales": "model.safetensors",
678
+ "tts_language_model.layers.11.self_attn.o_proj.weight": "model.safetensors",
679
+ "tts_language_model.layers.11.self_attn.q_proj.bias": "model.safetensors",
680
+ "tts_language_model.layers.11.self_attn.q_proj.biases": "model.safetensors",
681
+ "tts_language_model.layers.11.self_attn.q_proj.scales": "model.safetensors",
682
+ "tts_language_model.layers.11.self_attn.q_proj.weight": "model.safetensors",
683
+ "tts_language_model.layers.11.self_attn.v_proj.bias": "model.safetensors",
684
+ "tts_language_model.layers.11.self_attn.v_proj.biases": "model.safetensors",
685
+ "tts_language_model.layers.11.self_attn.v_proj.scales": "model.safetensors",
686
+ "tts_language_model.layers.11.self_attn.v_proj.weight": "model.safetensors",
687
+ "tts_language_model.layers.12.input_layernorm.weight": "model.safetensors",
688
+ "tts_language_model.layers.12.mlp.down_proj.biases": "model.safetensors",
689
+ "tts_language_model.layers.12.mlp.down_proj.scales": "model.safetensors",
690
+ "tts_language_model.layers.12.mlp.down_proj.weight": "model.safetensors",
691
+ "tts_language_model.layers.12.mlp.gate_proj.biases": "model.safetensors",
692
+ "tts_language_model.layers.12.mlp.gate_proj.scales": "model.safetensors",
693
+ "tts_language_model.layers.12.mlp.gate_proj.weight": "model.safetensors",
694
+ "tts_language_model.layers.12.mlp.up_proj.biases": "model.safetensors",
695
+ "tts_language_model.layers.12.mlp.up_proj.scales": "model.safetensors",
696
+ "tts_language_model.layers.12.mlp.up_proj.weight": "model.safetensors",
697
+ "tts_language_model.layers.12.post_attention_layernorm.weight": "model.safetensors",
698
+ "tts_language_model.layers.12.self_attn.k_proj.bias": "model.safetensors",
699
+ "tts_language_model.layers.12.self_attn.k_proj.biases": "model.safetensors",
700
+ "tts_language_model.layers.12.self_attn.k_proj.scales": "model.safetensors",
701
+ "tts_language_model.layers.12.self_attn.k_proj.weight": "model.safetensors",
702
+ "tts_language_model.layers.12.self_attn.o_proj.biases": "model.safetensors",
703
+ "tts_language_model.layers.12.self_attn.o_proj.scales": "model.safetensors",
704
+ "tts_language_model.layers.12.self_attn.o_proj.weight": "model.safetensors",
705
+ "tts_language_model.layers.12.self_attn.q_proj.bias": "model.safetensors",
706
+ "tts_language_model.layers.12.self_attn.q_proj.biases": "model.safetensors",
707
+ "tts_language_model.layers.12.self_attn.q_proj.scales": "model.safetensors",
708
+ "tts_language_model.layers.12.self_attn.q_proj.weight": "model.safetensors",
709
+ "tts_language_model.layers.12.self_attn.v_proj.bias": "model.safetensors",
710
+ "tts_language_model.layers.12.self_attn.v_proj.biases": "model.safetensors",
711
+ "tts_language_model.layers.12.self_attn.v_proj.scales": "model.safetensors",
712
+ "tts_language_model.layers.12.self_attn.v_proj.weight": "model.safetensors",
713
+ "tts_language_model.layers.13.input_layernorm.weight": "model.safetensors",
714
+ "tts_language_model.layers.13.mlp.down_proj.biases": "model.safetensors",
715
+ "tts_language_model.layers.13.mlp.down_proj.scales": "model.safetensors",
716
+ "tts_language_model.layers.13.mlp.down_proj.weight": "model.safetensors",
717
+ "tts_language_model.layers.13.mlp.gate_proj.biases": "model.safetensors",
718
+ "tts_language_model.layers.13.mlp.gate_proj.scales": "model.safetensors",
719
+ "tts_language_model.layers.13.mlp.gate_proj.weight": "model.safetensors",
720
+ "tts_language_model.layers.13.mlp.up_proj.biases": "model.safetensors",
721
+ "tts_language_model.layers.13.mlp.up_proj.scales": "model.safetensors",
722
+ "tts_language_model.layers.13.mlp.up_proj.weight": "model.safetensors",
723
+ "tts_language_model.layers.13.post_attention_layernorm.weight": "model.safetensors",
724
+ "tts_language_model.layers.13.self_attn.k_proj.bias": "model.safetensors",
725
+ "tts_language_model.layers.13.self_attn.k_proj.biases": "model.safetensors",
726
+ "tts_language_model.layers.13.self_attn.k_proj.scales": "model.safetensors",
727
+ "tts_language_model.layers.13.self_attn.k_proj.weight": "model.safetensors",
728
+ "tts_language_model.layers.13.self_attn.o_proj.biases": "model.safetensors",
729
+ "tts_language_model.layers.13.self_attn.o_proj.scales": "model.safetensors",
730
+ "tts_language_model.layers.13.self_attn.o_proj.weight": "model.safetensors",
731
+ "tts_language_model.layers.13.self_attn.q_proj.bias": "model.safetensors",
732
+ "tts_language_model.layers.13.self_attn.q_proj.biases": "model.safetensors",
733
+ "tts_language_model.layers.13.self_attn.q_proj.scales": "model.safetensors",
734
+ "tts_language_model.layers.13.self_attn.q_proj.weight": "model.safetensors",
735
+ "tts_language_model.layers.13.self_attn.v_proj.bias": "model.safetensors",
736
+ "tts_language_model.layers.13.self_attn.v_proj.biases": "model.safetensors",
737
+ "tts_language_model.layers.13.self_attn.v_proj.scales": "model.safetensors",
738
+ "tts_language_model.layers.13.self_attn.v_proj.weight": "model.safetensors",
739
+ "tts_language_model.layers.14.input_layernorm.weight": "model.safetensors",
740
+ "tts_language_model.layers.14.mlp.down_proj.biases": "model.safetensors",
741
+ "tts_language_model.layers.14.mlp.down_proj.scales": "model.safetensors",
742
+ "tts_language_model.layers.14.mlp.down_proj.weight": "model.safetensors",
743
+ "tts_language_model.layers.14.mlp.gate_proj.biases": "model.safetensors",
744
+ "tts_language_model.layers.14.mlp.gate_proj.scales": "model.safetensors",
745
+ "tts_language_model.layers.14.mlp.gate_proj.weight": "model.safetensors",
746
+ "tts_language_model.layers.14.mlp.up_proj.biases": "model.safetensors",
747
+ "tts_language_model.layers.14.mlp.up_proj.scales": "model.safetensors",
748
+ "tts_language_model.layers.14.mlp.up_proj.weight": "model.safetensors",
749
+ "tts_language_model.layers.14.post_attention_layernorm.weight": "model.safetensors",
750
+ "tts_language_model.layers.14.self_attn.k_proj.bias": "model.safetensors",
751
+ "tts_language_model.layers.14.self_attn.k_proj.biases": "model.safetensors",
752
+ "tts_language_model.layers.14.self_attn.k_proj.scales": "model.safetensors",
753
+ "tts_language_model.layers.14.self_attn.k_proj.weight": "model.safetensors",
754
+ "tts_language_model.layers.14.self_attn.o_proj.biases": "model.safetensors",
755
+ "tts_language_model.layers.14.self_attn.o_proj.scales": "model.safetensors",
756
+ "tts_language_model.layers.14.self_attn.o_proj.weight": "model.safetensors",
757
+ "tts_language_model.layers.14.self_attn.q_proj.bias": "model.safetensors",
758
+ "tts_language_model.layers.14.self_attn.q_proj.biases": "model.safetensors",
759
+ "tts_language_model.layers.14.self_attn.q_proj.scales": "model.safetensors",
760
+ "tts_language_model.layers.14.self_attn.q_proj.weight": "model.safetensors",
761
+ "tts_language_model.layers.14.self_attn.v_proj.bias": "model.safetensors",
762
+ "tts_language_model.layers.14.self_attn.v_proj.biases": "model.safetensors",
763
+ "tts_language_model.layers.14.self_attn.v_proj.scales": "model.safetensors",
764
+ "tts_language_model.layers.14.self_attn.v_proj.weight": "model.safetensors",
765
+ "tts_language_model.layers.15.input_layernorm.weight": "model.safetensors",
766
+ "tts_language_model.layers.15.mlp.down_proj.biases": "model.safetensors",
767
+ "tts_language_model.layers.15.mlp.down_proj.scales": "model.safetensors",
768
+ "tts_language_model.layers.15.mlp.down_proj.weight": "model.safetensors",
769
+ "tts_language_model.layers.15.mlp.gate_proj.biases": "model.safetensors",
770
+ "tts_language_model.layers.15.mlp.gate_proj.scales": "model.safetensors",
771
+ "tts_language_model.layers.15.mlp.gate_proj.weight": "model.safetensors",
772
+ "tts_language_model.layers.15.mlp.up_proj.biases": "model.safetensors",
773
+ "tts_language_model.layers.15.mlp.up_proj.scales": "model.safetensors",
774
+ "tts_language_model.layers.15.mlp.up_proj.weight": "model.safetensors",
775
+ "tts_language_model.layers.15.post_attention_layernorm.weight": "model.safetensors",
776
+ "tts_language_model.layers.15.self_attn.k_proj.bias": "model.safetensors",
777
+ "tts_language_model.layers.15.self_attn.k_proj.biases": "model.safetensors",
778
+ "tts_language_model.layers.15.self_attn.k_proj.scales": "model.safetensors",
779
+ "tts_language_model.layers.15.self_attn.k_proj.weight": "model.safetensors",
780
+ "tts_language_model.layers.15.self_attn.o_proj.biases": "model.safetensors",
781
+ "tts_language_model.layers.15.self_attn.o_proj.scales": "model.safetensors",
782
+ "tts_language_model.layers.15.self_attn.o_proj.weight": "model.safetensors",
783
+ "tts_language_model.layers.15.self_attn.q_proj.bias": "model.safetensors",
784
+ "tts_language_model.layers.15.self_attn.q_proj.biases": "model.safetensors",
785
+ "tts_language_model.layers.15.self_attn.q_proj.scales": "model.safetensors",
786
+ "tts_language_model.layers.15.self_attn.q_proj.weight": "model.safetensors",
787
+ "tts_language_model.layers.15.self_attn.v_proj.bias": "model.safetensors",
788
+ "tts_language_model.layers.15.self_attn.v_proj.biases": "model.safetensors",
789
+ "tts_language_model.layers.15.self_attn.v_proj.scales": "model.safetensors",
790
+ "tts_language_model.layers.15.self_attn.v_proj.weight": "model.safetensors",
791
+ "tts_language_model.layers.16.input_layernorm.weight": "model.safetensors",
792
+ "tts_language_model.layers.16.mlp.down_proj.biases": "model.safetensors",
793
+ "tts_language_model.layers.16.mlp.down_proj.scales": "model.safetensors",
794
+ "tts_language_model.layers.16.mlp.down_proj.weight": "model.safetensors",
795
+ "tts_language_model.layers.16.mlp.gate_proj.biases": "model.safetensors",
796
+ "tts_language_model.layers.16.mlp.gate_proj.scales": "model.safetensors",
797
+ "tts_language_model.layers.16.mlp.gate_proj.weight": "model.safetensors",
798
+ "tts_language_model.layers.16.mlp.up_proj.biases": "model.safetensors",
799
+ "tts_language_model.layers.16.mlp.up_proj.scales": "model.safetensors",
800
+ "tts_language_model.layers.16.mlp.up_proj.weight": "model.safetensors",
801
+ "tts_language_model.layers.16.post_attention_layernorm.weight": "model.safetensors",
802
+ "tts_language_model.layers.16.self_attn.k_proj.bias": "model.safetensors",
803
+ "tts_language_model.layers.16.self_attn.k_proj.biases": "model.safetensors",
804
+ "tts_language_model.layers.16.self_attn.k_proj.scales": "model.safetensors",
805
+ "tts_language_model.layers.16.self_attn.k_proj.weight": "model.safetensors",
806
+ "tts_language_model.layers.16.self_attn.o_proj.biases": "model.safetensors",
807
+ "tts_language_model.layers.16.self_attn.o_proj.scales": "model.safetensors",
808
+ "tts_language_model.layers.16.self_attn.o_proj.weight": "model.safetensors",
809
+ "tts_language_model.layers.16.self_attn.q_proj.bias": "model.safetensors",
810
+ "tts_language_model.layers.16.self_attn.q_proj.biases": "model.safetensors",
811
+ "tts_language_model.layers.16.self_attn.q_proj.scales": "model.safetensors",
812
+ "tts_language_model.layers.16.self_attn.q_proj.weight": "model.safetensors",
813
+ "tts_language_model.layers.16.self_attn.v_proj.bias": "model.safetensors",
814
+ "tts_language_model.layers.16.self_attn.v_proj.biases": "model.safetensors",
815
+ "tts_language_model.layers.16.self_attn.v_proj.scales": "model.safetensors",
816
+ "tts_language_model.layers.16.self_attn.v_proj.weight": "model.safetensors",
817
+ "tts_language_model.layers.17.input_layernorm.weight": "model.safetensors",
818
+ "tts_language_model.layers.17.mlp.down_proj.biases": "model.safetensors",
819
+ "tts_language_model.layers.17.mlp.down_proj.scales": "model.safetensors",
820
+ "tts_language_model.layers.17.mlp.down_proj.weight": "model.safetensors",
821
+ "tts_language_model.layers.17.mlp.gate_proj.biases": "model.safetensors",
822
+ "tts_language_model.layers.17.mlp.gate_proj.scales": "model.safetensors",
823
+ "tts_language_model.layers.17.mlp.gate_proj.weight": "model.safetensors",
824
+ "tts_language_model.layers.17.mlp.up_proj.biases": "model.safetensors",
825
+ "tts_language_model.layers.17.mlp.up_proj.scales": "model.safetensors",
826
+ "tts_language_model.layers.17.mlp.up_proj.weight": "model.safetensors",
827
+ "tts_language_model.layers.17.post_attention_layernorm.weight": "model.safetensors",
828
+ "tts_language_model.layers.17.self_attn.k_proj.bias": "model.safetensors",
829
+ "tts_language_model.layers.17.self_attn.k_proj.biases": "model.safetensors",
830
+ "tts_language_model.layers.17.self_attn.k_proj.scales": "model.safetensors",
831
+ "tts_language_model.layers.17.self_attn.k_proj.weight": "model.safetensors",
832
+ "tts_language_model.layers.17.self_attn.o_proj.biases": "model.safetensors",
833
+ "tts_language_model.layers.17.self_attn.o_proj.scales": "model.safetensors",
834
+ "tts_language_model.layers.17.self_attn.o_proj.weight": "model.safetensors",
835
+ "tts_language_model.layers.17.self_attn.q_proj.bias": "model.safetensors",
836
+ "tts_language_model.layers.17.self_attn.q_proj.biases": "model.safetensors",
837
+ "tts_language_model.layers.17.self_attn.q_proj.scales": "model.safetensors",
838
+ "tts_language_model.layers.17.self_attn.q_proj.weight": "model.safetensors",
839
+ "tts_language_model.layers.17.self_attn.v_proj.bias": "model.safetensors",
840
+ "tts_language_model.layers.17.self_attn.v_proj.biases": "model.safetensors",
841
+ "tts_language_model.layers.17.self_attn.v_proj.scales": "model.safetensors",
842
+ "tts_language_model.layers.17.self_attn.v_proj.weight": "model.safetensors",
843
+ "tts_language_model.layers.18.input_layernorm.weight": "model.safetensors",
844
+ "tts_language_model.layers.18.mlp.down_proj.biases": "model.safetensors",
845
+ "tts_language_model.layers.18.mlp.down_proj.scales": "model.safetensors",
846
+ "tts_language_model.layers.18.mlp.down_proj.weight": "model.safetensors",
847
+ "tts_language_model.layers.18.mlp.gate_proj.biases": "model.safetensors",
848
+ "tts_language_model.layers.18.mlp.gate_proj.scales": "model.safetensors",
849
+ "tts_language_model.layers.18.mlp.gate_proj.weight": "model.safetensors",
850
+ "tts_language_model.layers.18.mlp.up_proj.biases": "model.safetensors",
851
+ "tts_language_model.layers.18.mlp.up_proj.scales": "model.safetensors",
852
+ "tts_language_model.layers.18.mlp.up_proj.weight": "model.safetensors",
853
+ "tts_language_model.layers.18.post_attention_layernorm.weight": "model.safetensors",
854
+ "tts_language_model.layers.18.self_attn.k_proj.bias": "model.safetensors",
855
+ "tts_language_model.layers.18.self_attn.k_proj.biases": "model.safetensors",
856
+ "tts_language_model.layers.18.self_attn.k_proj.scales": "model.safetensors",
857
+ "tts_language_model.layers.18.self_attn.k_proj.weight": "model.safetensors",
858
+ "tts_language_model.layers.18.self_attn.o_proj.biases": "model.safetensors",
859
+ "tts_language_model.layers.18.self_attn.o_proj.scales": "model.safetensors",
860
+ "tts_language_model.layers.18.self_attn.o_proj.weight": "model.safetensors",
861
+ "tts_language_model.layers.18.self_attn.q_proj.bias": "model.safetensors",
862
+ "tts_language_model.layers.18.self_attn.q_proj.biases": "model.safetensors",
863
+ "tts_language_model.layers.18.self_attn.q_proj.scales": "model.safetensors",
864
+ "tts_language_model.layers.18.self_attn.q_proj.weight": "model.safetensors",
865
+ "tts_language_model.layers.18.self_attn.v_proj.bias": "model.safetensors",
866
+ "tts_language_model.layers.18.self_attn.v_proj.biases": "model.safetensors",
867
+ "tts_language_model.layers.18.self_attn.v_proj.scales": "model.safetensors",
868
+ "tts_language_model.layers.18.self_attn.v_proj.weight": "model.safetensors",
869
+ "tts_language_model.layers.19.input_layernorm.weight": "model.safetensors",
870
+ "tts_language_model.layers.19.mlp.down_proj.biases": "model.safetensors",
871
+ "tts_language_model.layers.19.mlp.down_proj.scales": "model.safetensors",
872
+ "tts_language_model.layers.19.mlp.down_proj.weight": "model.safetensors",
873
+ "tts_language_model.layers.19.mlp.gate_proj.biases": "model.safetensors",
874
+ "tts_language_model.layers.19.mlp.gate_proj.scales": "model.safetensors",
875
+ "tts_language_model.layers.19.mlp.gate_proj.weight": "model.safetensors",
876
+ "tts_language_model.layers.19.mlp.up_proj.biases": "model.safetensors",
877
+ "tts_language_model.layers.19.mlp.up_proj.scales": "model.safetensors",
878
+ "tts_language_model.layers.19.mlp.up_proj.weight": "model.safetensors",
879
+ "tts_language_model.layers.19.post_attention_layernorm.weight": "model.safetensors",
880
+ "tts_language_model.layers.19.self_attn.k_proj.bias": "model.safetensors",
881
+ "tts_language_model.layers.19.self_attn.k_proj.biases": "model.safetensors",
882
+ "tts_language_model.layers.19.self_attn.k_proj.scales": "model.safetensors",
883
+ "tts_language_model.layers.19.self_attn.k_proj.weight": "model.safetensors",
884
+ "tts_language_model.layers.19.self_attn.o_proj.biases": "model.safetensors",
885
+ "tts_language_model.layers.19.self_attn.o_proj.scales": "model.safetensors",
886
+ "tts_language_model.layers.19.self_attn.o_proj.weight": "model.safetensors",
887
+ "tts_language_model.layers.19.self_attn.q_proj.bias": "model.safetensors",
888
+ "tts_language_model.layers.19.self_attn.q_proj.biases": "model.safetensors",
889
+ "tts_language_model.layers.19.self_attn.q_proj.scales": "model.safetensors",
890
+ "tts_language_model.layers.19.self_attn.q_proj.weight": "model.safetensors",
891
+ "tts_language_model.layers.19.self_attn.v_proj.bias": "model.safetensors",
892
+ "tts_language_model.layers.19.self_attn.v_proj.biases": "model.safetensors",
893
+ "tts_language_model.layers.19.self_attn.v_proj.scales": "model.safetensors",
894
+ "tts_language_model.layers.19.self_attn.v_proj.weight": "model.safetensors",
895
+ "tts_language_model.layers.2.input_layernorm.weight": "model.safetensors",
896
+ "tts_language_model.layers.2.mlp.down_proj.biases": "model.safetensors",
897
+ "tts_language_model.layers.2.mlp.down_proj.scales": "model.safetensors",
898
+ "tts_language_model.layers.2.mlp.down_proj.weight": "model.safetensors",
899
+ "tts_language_model.layers.2.mlp.gate_proj.biases": "model.safetensors",
900
+ "tts_language_model.layers.2.mlp.gate_proj.scales": "model.safetensors",
901
+ "tts_language_model.layers.2.mlp.gate_proj.weight": "model.safetensors",
902
+ "tts_language_model.layers.2.mlp.up_proj.biases": "model.safetensors",
903
+ "tts_language_model.layers.2.mlp.up_proj.scales": "model.safetensors",
904
+ "tts_language_model.layers.2.mlp.up_proj.weight": "model.safetensors",
905
+ "tts_language_model.layers.2.post_attention_layernorm.weight": "model.safetensors",
906
+ "tts_language_model.layers.2.self_attn.k_proj.bias": "model.safetensors",
907
+ "tts_language_model.layers.2.self_attn.k_proj.biases": "model.safetensors",
908
+ "tts_language_model.layers.2.self_attn.k_proj.scales": "model.safetensors",
909
+ "tts_language_model.layers.2.self_attn.k_proj.weight": "model.safetensors",
910
+ "tts_language_model.layers.2.self_attn.o_proj.biases": "model.safetensors",
911
+ "tts_language_model.layers.2.self_attn.o_proj.scales": "model.safetensors",
912
+ "tts_language_model.layers.2.self_attn.o_proj.weight": "model.safetensors",
913
+ "tts_language_model.layers.2.self_attn.q_proj.bias": "model.safetensors",
914
+ "tts_language_model.layers.2.self_attn.q_proj.biases": "model.safetensors",
915
+ "tts_language_model.layers.2.self_attn.q_proj.scales": "model.safetensors",
916
+ "tts_language_model.layers.2.self_attn.q_proj.weight": "model.safetensors",
917
+ "tts_language_model.layers.2.self_attn.v_proj.bias": "model.safetensors",
918
+ "tts_language_model.layers.2.self_attn.v_proj.biases": "model.safetensors",
919
+ "tts_language_model.layers.2.self_attn.v_proj.scales": "model.safetensors",
920
+ "tts_language_model.layers.2.self_attn.v_proj.weight": "model.safetensors",
921
+ "tts_language_model.layers.3.input_layernorm.weight": "model.safetensors",
922
+ "tts_language_model.layers.3.mlp.down_proj.biases": "model.safetensors",
923
+ "tts_language_model.layers.3.mlp.down_proj.scales": "model.safetensors",
924
+ "tts_language_model.layers.3.mlp.down_proj.weight": "model.safetensors",
925
+ "tts_language_model.layers.3.mlp.gate_proj.biases": "model.safetensors",
926
+ "tts_language_model.layers.3.mlp.gate_proj.scales": "model.safetensors",
927
+ "tts_language_model.layers.3.mlp.gate_proj.weight": "model.safetensors",
928
+ "tts_language_model.layers.3.mlp.up_proj.biases": "model.safetensors",
929
+ "tts_language_model.layers.3.mlp.up_proj.scales": "model.safetensors",
930
+ "tts_language_model.layers.3.mlp.up_proj.weight": "model.safetensors",
931
+ "tts_language_model.layers.3.post_attention_layernorm.weight": "model.safetensors",
932
+ "tts_language_model.layers.3.self_attn.k_proj.bias": "model.safetensors",
933
+ "tts_language_model.layers.3.self_attn.k_proj.biases": "model.safetensors",
934
+ "tts_language_model.layers.3.self_attn.k_proj.scales": "model.safetensors",
935
+ "tts_language_model.layers.3.self_attn.k_proj.weight": "model.safetensors",
936
+ "tts_language_model.layers.3.self_attn.o_proj.biases": "model.safetensors",
937
+ "tts_language_model.layers.3.self_attn.o_proj.scales": "model.safetensors",
938
+ "tts_language_model.layers.3.self_attn.o_proj.weight": "model.safetensors",
939
+ "tts_language_model.layers.3.self_attn.q_proj.bias": "model.safetensors",
940
+ "tts_language_model.layers.3.self_attn.q_proj.biases": "model.safetensors",
941
+ "tts_language_model.layers.3.self_attn.q_proj.scales": "model.safetensors",
942
+ "tts_language_model.layers.3.self_attn.q_proj.weight": "model.safetensors",
943
+ "tts_language_model.layers.3.self_attn.v_proj.bias": "model.safetensors",
944
+ "tts_language_model.layers.3.self_attn.v_proj.biases": "model.safetensors",
945
+ "tts_language_model.layers.3.self_attn.v_proj.scales": "model.safetensors",
946
+ "tts_language_model.layers.3.self_attn.v_proj.weight": "model.safetensors",
947
+ "tts_language_model.layers.4.input_layernorm.weight": "model.safetensors",
948
+ "tts_language_model.layers.4.mlp.down_proj.biases": "model.safetensors",
949
+ "tts_language_model.layers.4.mlp.down_proj.scales": "model.safetensors",
950
+ "tts_language_model.layers.4.mlp.down_proj.weight": "model.safetensors",
951
+ "tts_language_model.layers.4.mlp.gate_proj.biases": "model.safetensors",
952
+ "tts_language_model.layers.4.mlp.gate_proj.scales": "model.safetensors",
953
+ "tts_language_model.layers.4.mlp.gate_proj.weight": "model.safetensors",
954
+ "tts_language_model.layers.4.mlp.up_proj.biases": "model.safetensors",
955
+ "tts_language_model.layers.4.mlp.up_proj.scales": "model.safetensors",
956
+ "tts_language_model.layers.4.mlp.up_proj.weight": "model.safetensors",
957
+ "tts_language_model.layers.4.post_attention_layernorm.weight": "model.safetensors",
958
+ "tts_language_model.layers.4.self_attn.k_proj.bias": "model.safetensors",
959
+ "tts_language_model.layers.4.self_attn.k_proj.biases": "model.safetensors",
960
+ "tts_language_model.layers.4.self_attn.k_proj.scales": "model.safetensors",
961
+ "tts_language_model.layers.4.self_attn.k_proj.weight": "model.safetensors",
962
+ "tts_language_model.layers.4.self_attn.o_proj.biases": "model.safetensors",
963
+ "tts_language_model.layers.4.self_attn.o_proj.scales": "model.safetensors",
964
+ "tts_language_model.layers.4.self_attn.o_proj.weight": "model.safetensors",
965
+ "tts_language_model.layers.4.self_attn.q_proj.bias": "model.safetensors",
966
+ "tts_language_model.layers.4.self_attn.q_proj.biases": "model.safetensors",
967
+ "tts_language_model.layers.4.self_attn.q_proj.scales": "model.safetensors",
968
+ "tts_language_model.layers.4.self_attn.q_proj.weight": "model.safetensors",
969
+ "tts_language_model.layers.4.self_attn.v_proj.bias": "model.safetensors",
970
+ "tts_language_model.layers.4.self_attn.v_proj.biases": "model.safetensors",
971
+ "tts_language_model.layers.4.self_attn.v_proj.scales": "model.safetensors",
972
+ "tts_language_model.layers.4.self_attn.v_proj.weight": "model.safetensors",
973
+ "tts_language_model.layers.5.input_layernorm.weight": "model.safetensors",
974
+ "tts_language_model.layers.5.mlp.down_proj.biases": "model.safetensors",
975
+ "tts_language_model.layers.5.mlp.down_proj.scales": "model.safetensors",
976
+ "tts_language_model.layers.5.mlp.down_proj.weight": "model.safetensors",
977
+ "tts_language_model.layers.5.mlp.gate_proj.biases": "model.safetensors",
978
+ "tts_language_model.layers.5.mlp.gate_proj.scales": "model.safetensors",
979
+ "tts_language_model.layers.5.mlp.gate_proj.weight": "model.safetensors",
980
+ "tts_language_model.layers.5.mlp.up_proj.biases": "model.safetensors",
981
+ "tts_language_model.layers.5.mlp.up_proj.scales": "model.safetensors",
982
+ "tts_language_model.layers.5.mlp.up_proj.weight": "model.safetensors",
983
+ "tts_language_model.layers.5.post_attention_layernorm.weight": "model.safetensors",
984
+ "tts_language_model.layers.5.self_attn.k_proj.bias": "model.safetensors",
985
+ "tts_language_model.layers.5.self_attn.k_proj.biases": "model.safetensors",
986
+ "tts_language_model.layers.5.self_attn.k_proj.scales": "model.safetensors",
987
+ "tts_language_model.layers.5.self_attn.k_proj.weight": "model.safetensors",
988
+ "tts_language_model.layers.5.self_attn.o_proj.biases": "model.safetensors",
989
+ "tts_language_model.layers.5.self_attn.o_proj.scales": "model.safetensors",
990
+ "tts_language_model.layers.5.self_attn.o_proj.weight": "model.safetensors",
991
+ "tts_language_model.layers.5.self_attn.q_proj.bias": "model.safetensors",
992
+ "tts_language_model.layers.5.self_attn.q_proj.biases": "model.safetensors",
993
+ "tts_language_model.layers.5.self_attn.q_proj.scales": "model.safetensors",
994
+ "tts_language_model.layers.5.self_attn.q_proj.weight": "model.safetensors",
995
+ "tts_language_model.layers.5.self_attn.v_proj.bias": "model.safetensors",
996
+ "tts_language_model.layers.5.self_attn.v_proj.biases": "model.safetensors",
997
+ "tts_language_model.layers.5.self_attn.v_proj.scales": "model.safetensors",
998
+ "tts_language_model.layers.5.self_attn.v_proj.weight": "model.safetensors",
999
+ "tts_language_model.layers.6.input_layernorm.weight": "model.safetensors",
1000
+ "tts_language_model.layers.6.mlp.down_proj.biases": "model.safetensors",
1001
+ "tts_language_model.layers.6.mlp.down_proj.scales": "model.safetensors",
1002
+ "tts_language_model.layers.6.mlp.down_proj.weight": "model.safetensors",
1003
+ "tts_language_model.layers.6.mlp.gate_proj.biases": "model.safetensors",
1004
+ "tts_language_model.layers.6.mlp.gate_proj.scales": "model.safetensors",
1005
+ "tts_language_model.layers.6.mlp.gate_proj.weight": "model.safetensors",
1006
+ "tts_language_model.layers.6.mlp.up_proj.biases": "model.safetensors",
1007
+ "tts_language_model.layers.6.mlp.up_proj.scales": "model.safetensors",
1008
+ "tts_language_model.layers.6.mlp.up_proj.weight": "model.safetensors",
1009
+ "tts_language_model.layers.6.post_attention_layernorm.weight": "model.safetensors",
1010
+ "tts_language_model.layers.6.self_attn.k_proj.bias": "model.safetensors",
1011
+ "tts_language_model.layers.6.self_attn.k_proj.biases": "model.safetensors",
1012
+ "tts_language_model.layers.6.self_attn.k_proj.scales": "model.safetensors",
1013
+ "tts_language_model.layers.6.self_attn.k_proj.weight": "model.safetensors",
1014
+ "tts_language_model.layers.6.self_attn.o_proj.biases": "model.safetensors",
1015
+ "tts_language_model.layers.6.self_attn.o_proj.scales": "model.safetensors",
1016
+ "tts_language_model.layers.6.self_attn.o_proj.weight": "model.safetensors",
1017
+ "tts_language_model.layers.6.self_attn.q_proj.bias": "model.safetensors",
1018
+ "tts_language_model.layers.6.self_attn.q_proj.biases": "model.safetensors",
1019
+ "tts_language_model.layers.6.self_attn.q_proj.scales": "model.safetensors",
1020
+ "tts_language_model.layers.6.self_attn.q_proj.weight": "model.safetensors",
1021
+ "tts_language_model.layers.6.self_attn.v_proj.bias": "model.safetensors",
1022
+ "tts_language_model.layers.6.self_attn.v_proj.biases": "model.safetensors",
1023
+ "tts_language_model.layers.6.self_attn.v_proj.scales": "model.safetensors",
1024
+ "tts_language_model.layers.6.self_attn.v_proj.weight": "model.safetensors",
1025
+ "tts_language_model.layers.7.input_layernorm.weight": "model.safetensors",
1026
+ "tts_language_model.layers.7.mlp.down_proj.biases": "model.safetensors",
1027
+ "tts_language_model.layers.7.mlp.down_proj.scales": "model.safetensors",
1028
+ "tts_language_model.layers.7.mlp.down_proj.weight": "model.safetensors",
1029
+ "tts_language_model.layers.7.mlp.gate_proj.biases": "model.safetensors",
1030
+ "tts_language_model.layers.7.mlp.gate_proj.scales": "model.safetensors",
1031
+ "tts_language_model.layers.7.mlp.gate_proj.weight": "model.safetensors",
1032
+ "tts_language_model.layers.7.mlp.up_proj.biases": "model.safetensors",
1033
+ "tts_language_model.layers.7.mlp.up_proj.scales": "model.safetensors",
1034
+ "tts_language_model.layers.7.mlp.up_proj.weight": "model.safetensors",
1035
+ "tts_language_model.layers.7.post_attention_layernorm.weight": "model.safetensors",
1036
+ "tts_language_model.layers.7.self_attn.k_proj.bias": "model.safetensors",
1037
+ "tts_language_model.layers.7.self_attn.k_proj.biases": "model.safetensors",
1038
+ "tts_language_model.layers.7.self_attn.k_proj.scales": "model.safetensors",
1039
+ "tts_language_model.layers.7.self_attn.k_proj.weight": "model.safetensors",
1040
+ "tts_language_model.layers.7.self_attn.o_proj.biases": "model.safetensors",
1041
+ "tts_language_model.layers.7.self_attn.o_proj.scales": "model.safetensors",
1042
+ "tts_language_model.layers.7.self_attn.o_proj.weight": "model.safetensors",
1043
+ "tts_language_model.layers.7.self_attn.q_proj.bias": "model.safetensors",
1044
+ "tts_language_model.layers.7.self_attn.q_proj.biases": "model.safetensors",
1045
+ "tts_language_model.layers.7.self_attn.q_proj.scales": "model.safetensors",
1046
+ "tts_language_model.layers.7.self_attn.q_proj.weight": "model.safetensors",
1047
+ "tts_language_model.layers.7.self_attn.v_proj.bias": "model.safetensors",
1048
+ "tts_language_model.layers.7.self_attn.v_proj.biases": "model.safetensors",
1049
+ "tts_language_model.layers.7.self_attn.v_proj.scales": "model.safetensors",
1050
+ "tts_language_model.layers.7.self_attn.v_proj.weight": "model.safetensors",
1051
+ "tts_language_model.layers.8.input_layernorm.weight": "model.safetensors",
1052
+ "tts_language_model.layers.8.mlp.down_proj.biases": "model.safetensors",
1053
+ "tts_language_model.layers.8.mlp.down_proj.scales": "model.safetensors",
1054
+ "tts_language_model.layers.8.mlp.down_proj.weight": "model.safetensors",
1055
+ "tts_language_model.layers.8.mlp.gate_proj.biases": "model.safetensors",
1056
+ "tts_language_model.layers.8.mlp.gate_proj.scales": "model.safetensors",
1057
+ "tts_language_model.layers.8.mlp.gate_proj.weight": "model.safetensors",
1058
+ "tts_language_model.layers.8.mlp.up_proj.biases": "model.safetensors",
1059
+ "tts_language_model.layers.8.mlp.up_proj.scales": "model.safetensors",
1060
+ "tts_language_model.layers.8.mlp.up_proj.weight": "model.safetensors",
1061
+ "tts_language_model.layers.8.post_attention_layernorm.weight": "model.safetensors",
1062
+ "tts_language_model.layers.8.self_attn.k_proj.bias": "model.safetensors",
1063
+ "tts_language_model.layers.8.self_attn.k_proj.biases": "model.safetensors",
1064
+ "tts_language_model.layers.8.self_attn.k_proj.scales": "model.safetensors",
1065
+ "tts_language_model.layers.8.self_attn.k_proj.weight": "model.safetensors",
1066
+ "tts_language_model.layers.8.self_attn.o_proj.biases": "model.safetensors",
1067
+ "tts_language_model.layers.8.self_attn.o_proj.scales": "model.safetensors",
1068
+ "tts_language_model.layers.8.self_attn.o_proj.weight": "model.safetensors",
1069
+ "tts_language_model.layers.8.self_attn.q_proj.bias": "model.safetensors",
1070
+ "tts_language_model.layers.8.self_attn.q_proj.biases": "model.safetensors",
1071
+ "tts_language_model.layers.8.self_attn.q_proj.scales": "model.safetensors",
1072
+ "tts_language_model.layers.8.self_attn.q_proj.weight": "model.safetensors",
1073
+ "tts_language_model.layers.8.self_attn.v_proj.bias": "model.safetensors",
1074
+ "tts_language_model.layers.8.self_attn.v_proj.biases": "model.safetensors",
1075
+ "tts_language_model.layers.8.self_attn.v_proj.scales": "model.safetensors",
1076
+ "tts_language_model.layers.8.self_attn.v_proj.weight": "model.safetensors",
1077
+ "tts_language_model.layers.9.input_layernorm.weight": "model.safetensors",
1078
+ "tts_language_model.layers.9.mlp.down_proj.biases": "model.safetensors",
1079
+ "tts_language_model.layers.9.mlp.down_proj.scales": "model.safetensors",
1080
+ "tts_language_model.layers.9.mlp.down_proj.weight": "model.safetensors",
1081
+ "tts_language_model.layers.9.mlp.gate_proj.biases": "model.safetensors",
1082
+ "tts_language_model.layers.9.mlp.gate_proj.scales": "model.safetensors",
1083
+ "tts_language_model.layers.9.mlp.gate_proj.weight": "model.safetensors",
1084
+ "tts_language_model.layers.9.mlp.up_proj.biases": "model.safetensors",
1085
+ "tts_language_model.layers.9.mlp.up_proj.scales": "model.safetensors",
1086
+ "tts_language_model.layers.9.mlp.up_proj.weight": "model.safetensors",
1087
+ "tts_language_model.layers.9.post_attention_layernorm.weight": "model.safetensors",
1088
+ "tts_language_model.layers.9.self_attn.k_proj.bias": "model.safetensors",
1089
+ "tts_language_model.layers.9.self_attn.k_proj.biases": "model.safetensors",
1090
+ "tts_language_model.layers.9.self_attn.k_proj.scales": "model.safetensors",
1091
+ "tts_language_model.layers.9.self_attn.k_proj.weight": "model.safetensors",
1092
+ "tts_language_model.layers.9.self_attn.o_proj.biases": "model.safetensors",
1093
+ "tts_language_model.layers.9.self_attn.o_proj.scales": "model.safetensors",
1094
+ "tts_language_model.layers.9.self_attn.o_proj.weight": "model.safetensors",
1095
+ "tts_language_model.layers.9.self_attn.q_proj.bias": "model.safetensors",
1096
+ "tts_language_model.layers.9.self_attn.q_proj.biases": "model.safetensors",
1097
+ "tts_language_model.layers.9.self_attn.q_proj.scales": "model.safetensors",
1098
+ "tts_language_model.layers.9.self_attn.q_proj.weight": "model.safetensors",
1099
+ "tts_language_model.layers.9.self_attn.v_proj.bias": "model.safetensors",
1100
+ "tts_language_model.layers.9.self_attn.v_proj.biases": "model.safetensors",
1101
+ "tts_language_model.layers.9.self_attn.v_proj.scales": "model.safetensors",
1102
+ "tts_language_model.layers.9.self_attn.v_proj.weight": "model.safetensors",
1103
+ "tts_language_model.norm.weight": "model.safetensors"
1104
+ }
1105
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "processor_class": "VibeVoiceStreamingProcessor",
3
+ "speech_tok_compress_ratio": 3200,
4
+ "db_normalize": true,
5
+ "audio_processor": {
6
+ "feature_extractor_type": "VibeVoiceTokenizerProcessor",
7
+ "sampling_rate": 24000,
8
+ "normalize_audio": true,
9
+ "target_dB_FS": -25,
10
+ "eps": 1e-06
11
+ },
12
+ "language_model_pretrained_name": "Qwen/Qwen2.5-0.5B"
13
+ }