diff --git a/model_specs/chatterbox.json b/model_specs/chatterbox.json index 67d9534dc..57ed1728a 100644 --- a/model_specs/chatterbox.json +++ b/model_specs/chatterbox.json @@ -101,7 +101,12 @@ "ve.safetensors", "t3_cfg.safetensors", "s3gen.safetensors", - "tokenizer.json" + "tokenizer.json", + "grapheme_mtl_merged_expanded_v1.json", + "Cangjie5_TC.json", + "conds.pt", + "t3_mtl23ls_v2.safetensors", + "t3_mtl23ls_v3.safetensors" ], "download": { "kind": "huggingface_snapshot", diff --git a/model_specs/index_tts2.json b/model_specs/index_tts2.json index 72c680eb8..4189d2bb0 100644 --- a/model_specs/index_tts2.json +++ b/model_specs/index_tts2.json @@ -96,7 +96,25 @@ "files": [ "config.yaml", "bpe.model", - "gpt.safetensors" + "gpt.safetensors", + "w2v-bert-2.0/config.json", + "w2v-bert-2.0/preprocessor_config.json", + "bigvgan/config.json", + "qwen0.6bemo4-merge/config.json", + "qwen0.6bemo4-merge/generation_config.json", + "qwen0.6bemo4-merge/tokenizer.json", + "qwen0.6bemo4-merge/tokenizer_config.json", + "qwen0.6bemo4-merge/vocab.json", + "qwen0.6bemo4-merge/merges.txt", + "s2mel.safetensors", + "feat1.safetensors", + "feat2.safetensors", + "wav2vec2bert_stats.safetensors", + "w2v-bert-2.0/model.safetensors", + "semantic_codec_model.safetensors", + "campplus.safetensors", + "bigvgan/model.safetensors", + "qwen0.6bemo4-merge/model.safetensors" ], "download": { "kind": "huggingface_snapshot", diff --git a/model_specs/omnivoice.json b/model_specs/omnivoice.json index 1f65bdb13..edbc851b7 100644 --- a/model_specs/omnivoice.json +++ b/model_specs/omnivoice.json @@ -97,7 +97,11 @@ "files": [ "config.json", "model.safetensors", - "tokenizer.json" + "tokenizer.json", + "tokenizer_config.json", + "audio_tokenizer/config.json", + "audio_tokenizer/preprocessor_config.json", + "audio_tokenizer/model.safetensors" ], "download": { "kind": "huggingface_snapshot", diff --git a/model_specs/qwen3_tts.json b/model_specs/qwen3_tts.json index 22d0e6dd9..fedc5e53d 100644 --- a/model_specs/qwen3_tts.json +++ b/model_specs/qwen3_tts.json @@ -172,7 +172,9 @@ "model.safetensors", "speech_tokenizer/config.json", "speech_tokenizer/model.safetensors", - "tokenizer_config.json" + "tokenizer_config.json", + "vocab.json", + "merges.txt" ], "download": { "kind": "huggingface_snapshot", diff --git a/model_specs/seed_vc.json b/model_specs/seed_vc.json index 0a0bebf1c..93b2d4333 100644 --- a/model_specs/seed_vc.json +++ b/model_specs/seed_vc.json @@ -202,7 +202,32 @@ "files": [ "seed_vc_manifest.json", "v2/ar.safetensors", - "v2/cfm.safetensors" + "v2/cfm.safetensors", + "v2/vc_wrapper.json", + "astral/bsq32.json", + "astral/bsq2048.json", + "v1/svc.json", + "v1/whisper_bigvgan.json", + "v1/xlsr_hift.json", + "hift/config.json", + "bigvgan/v2_22khz_80band_256x/config.json", + "bigvgan/v2_44khz_128band_512x/config.json", + "whisper-small/config.json", + "hubert-large-ll60k/config.json", + "wav2vec2-xls-r-300m/config.json", + "v1/svc.safetensors", + "v1/whisper_bigvgan.safetensors", + "v1/xlsr_hift.safetensors", + "astral/bsq32.safetensors", + "astral/bsq2048.safetensors", + "campplus/model.safetensors", + "rmvpe/model.safetensors", + "hift/model.safetensors", + "bigvgan/v2_22khz_80band_256x/model.safetensors", + "bigvgan/v2_44khz_128band_512x/model.safetensors", + "whisper-small/model.safetensors", + "hubert-large-ll60k/model.safetensors", + "wav2vec2-xls-r-300m/model.safetensors" ], "download": { "kind": "huggingface_snapshot", diff --git a/model_specs/supertonic.json b/model_specs/supertonic.json index 25ddbe992..36a09c678 100644 --- a/model_specs/supertonic.json +++ b/model_specs/supertonic.json @@ -120,7 +120,17 @@ "files": [ "config/tts.json", "config/unicode_indexer.json", - "ggml/supertonic.safetensors" + "ggml/supertonic.safetensors", + "voice_styles/F1.json", + "voice_styles/F2.json", + "voice_styles/F3.json", + "voice_styles/F4.json", + "voice_styles/F5.json", + "voice_styles/M1.json", + "voice_styles/M2.json", + "voice_styles/M3.json", + "voice_styles/M4.json", + "voice_styles/M5.json" ], "download": { "kind": "huggingface_snapshot",