Remove root-level files (moved to TTS/DiffRhythm/)

MuQ-MuLan-large/config.json

@@ -1,41 +0,0 @@
-{
-  "mulan": {
-    "sr": 24000,
-    "clip_secs": 10,
-    "dim_latent": 512,
-    "decoupled_contrastive_learning": true,
-    "hierarchical_contrastive_loss": false,
-    "hierarchical_contrastive_loss_layers": null,
-    "sigmoid_contrastive_loss": false,
-    "rank_contrast": true
-  },
-  "audio_model": {
-    "name": "OpenMuQ/MuQ-large-msd-iter",
-    "model_dim": 1024,
-    "use_layer_idx": -1
-  },
-  "text_model": {
-    "name": "xlm-roberta-base",
-    "model_dim": null,
-    "use_layer_idx": -1
-  },
-  "audio_transformer": {
-    "dim": 768,
-    "tf_depth": 0,
-    "heads": 8,
-    "dim_head": 64,
-    "attn_dropout": 0,
-    "ff_dropout": 0,
-    "ff_mult": 4
-  },
-  "text_transformer": {
-    "dim": 768,
-    "tf_depth": 8,
-    "max_seq_len": 1024,
-    "dim_head": 64,
-    "heads": 8,
-    "attn_dropout": 0,
-    "ff_dropout": 0,
-    "ff_mult": 4
-  }
-}

MuQ-MuLan-large/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d42ae3f7cb9b66759ee0089ddc70e2f28b130c2d8ba621457358272d32dd0444
-size 2653954401

MuQ-large-msd-iter/config.json

@@ -1,143 +0,0 @@
-{
-  "codebook_dim": 16,
-  "codebook_size": 8192,
-  "conv_dim": 512,
-  "encoder_depth": 12,
-  "encoder_dim": 1024,
-  "features": [
-    "melspec_2048"
-  ],
-  "hop_length": 240,
-  "is_flash": false,
-  "label_rate": 25,
-  "mask_hop": 0.4,
-  "mask_prob": 0.6,
-  "n_mels": 128,
-  "num_codebooks": 1,
-  "recon_loss_ratio": null,
-  "resume_checkpoint": null,
-  "rvq_ckpt_path": null,
-  "rvq_multi_layer_num": 1,
-  "rvq_n_codebooks": 8,
-  "stat": {
-    "melspec_2048_cnt": 14282760192,
-    "melspec_2048_mean": 6.768444971712967,
-    "melspec_2048_std": 18.417922652295623
-  },
-  "use_encodec_target": false,
-  "use_rvq_target": true,
-  "use_vq_target": false,
-  "w2v2_config": {
-    "activation_dropout": 0.1,
-    "adapter_kernel_size": 3,
-    "adapter_stride": 2,
-    "add_adapter": false,
-    "apply_spec_augment": true,
-    "architectures": [
-      "Wav2Vec2ConformerForCTC"
-    ],
-    "attention_dropout": 0.1,
-    "bos_token_id": 1,
-    "classifier_proj_size": 256,
-    "codevector_dim": 768,
-    "conformer_conv_dropout": 0.1,
-    "contrastive_logits_temperature": 0.1,
-    "conv_bias": true,
-    "conv_depthwise_kernel_size": 31,
-    "conv_dim": [
-      512,
-      512,
-      512,
-      512,
-      512,
-      512,
-      512
-    ],
-    "conv_kernel": [
-      10,
-      3,
-      3,
-      3,
-      3,
-      2,
-      2
-    ],
-    "conv_stride": [
-      5,
-      2,
-      2,
-      2,
-      2,
-      2,
-      2
-    ],
-    "ctc_loss_reduction": "sum",
-    "ctc_zero_infinity": false,
-    "diversity_loss_weight": 0.1,
-    "do_stable_layer_norm": true,
-    "eos_token_id": 2,
-    "feat_extract_activation": "gelu",
-    "feat_extract_dropout": 0.0,
-    "feat_extract_norm": "layer",
-    "feat_proj_dropout": 0.1,
-    "feat_quantizer_dropout": 0.0,
-    "final_dropout": 0.1,
-    "gradient_checkpointing": false,
-    "hidden_act": "swish",
-    "hidden_dropout": 0.1,
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 1024,
-    "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "layer_norm_eps": 1e-05,
-    "layerdrop": 0.0,
-    "mask_feature_length": 10,
-    "mask_feature_min_masks": 0,
-    "mask_feature_prob": 0.0,
-    "mask_time_length": 10,
-    "mask_time_min_masks": 2,
-    "mask_time_prob": 0.05,
-    "max_source_positions": 5000,
-    "model_type": "wav2vec2-conformer",
-    "num_adapter_layers": 3,
-    "num_attention_heads": 16,
-    "num_codevector_groups": 2,
-    "num_codevectors_per_group": 320,
-    "num_conv_pos_embedding_groups": 16,
-    "num_conv_pos_embeddings": 128,
-    "num_feat_extract_layers": 7,
-    "num_hidden_layers": 24,
-    "num_negatives": 100,
-    "output_hidden_size": 1024,
-    "pad_token_id": 0,
-    "position_embeddings_type": "rotary",
-    "proj_codevector_dim": 768,
-    "rotary_embedding_base": 10000,
-    "tdnn_dilation": [
-      1,
-      2,
-      3,
-      1,
-      1
-    ],
-    "tdnn_dim": [
-      512,
-      512,
-      512,
-      512,
-      1500
-    ],
-    "tdnn_kernel": [
-      5,
-      3,
-      3,
-      1,
-      1
-    ],
-    "torch_dtype": "float32",
-    "transformers_version": "4.19.0.dev0",
-    "use_weighted_layer_sum": false,
-    "vocab_size": 32,
-    "xvector_output_dim": 512
-  }
-}

MuQ-large-msd-iter/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:273febab2be02872c37d2c37e48a9d6c52c1c9392f3eeeabd498efa281ccb7a6
-size 1333825096

MuQ-large-msd-iter/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:334df3de2832ec1acfd8b6ce54e7de4073401fe821f7ec0ad0d954832be2d26a
-size 1333965438

cfm_model_v1_2.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e819b317ce2cf1fb22f386d74f351b697204ec1f57f03edfe50dbca71cf0768
-size 2218709125

config.json

@@ -1,13 +0,0 @@
-{
-    "model_type": "diffrhythm",
-    "model": {
-        "dim": 2048,
-        "depth": 16,
-        "heads": 32,
-        "ff_mult": 4,
-        "text_dim": 512,
-        "conv_layers": 4,
-        "mel_dim": 64,
-        "text_num_embeds": 363
-    }
-}

eval-model/eval.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:81cbd54af8b103251e425fcbd8f5313975cb742e760c3dae1e10f99969933fd6
-size 100792276

eval-model/eval.yaml

@@ -1,6 +0,0 @@
-generator:
-  _target_: pretrained.eval.Generator
-  in_features: 1024
-  ffd_hidden_size: 4096
-  num_classes: 5
-  attn_layer_num: 4

vae_model.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:712693f27299937c6ccf1a6d6f1d9b45c7c8c11210d3b0cbb0f36181465ba29f
-size 624520127

xlm-roberta-base/config.json

@@ -1,25 +0,0 @@
-{
-  "architectures": [
-    "XLMRobertaForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "transformers_version": "4.17.0.dev0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
-}

xlm-roberta-base/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6fd4797bc397c3b8b55d6bb5740366b57e6a3ce91c04c77f22aafc0c128e6feb
-size 1115567652

xlm-roberta-base/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9d83baaafea92d36de26002c8135a427d55ee6fdc4faaa6e400be4c47724a07e
-size 1115590446

xlm-roberta-base/sentencepiece.bpe.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
-size 5069051

xlm-roberta-base/tokenizer_config.json

@@ -1 +0,0 @@
-{"model_max_length": 512}