{
  "family": "vevo2",
  "display_name": "Vevo2",
  "description": "Unified controllable framework for English and Chinese speech and singing voice generation, voice conversion, and editing, with tokenizers that disentangle content, prosody, melody, style, and timbre.",
  "category": "voice_conversion",
  "status": "supported",
  "tasks": [
    "tts",
    "music",
    "vc",
    "edit",
    "svc",
    "s2s"
  ],
  "modes": [
    "offline"
  ],
  "languages": [
    "en",
    "zh"
  ],
  "capabilities": {
    "music": [
      "lyrics"
    ],
    "vc": [
      "speaker_reference"
    ],
    "svc": [
      "speaker_reference",
      "singing"
    ],
    "s2s": [
      "speaker_reference"
    ],
    "edit": [
      "prompt_editing"
    ]
  },
  "runtime": {
    "tags": [
      "gguf"
    ]
  },
  "ui": {
    "recommended_package": "vevo2_q8_0",
    "tags": [
      "TTS",
      "Music",
      "VC",
      "Edit",
      "GGUF"
    ],
    "docs": [
      "docs/models/vevo2.md",
      "docs/tts.md",
      "docs/gguf.md"
    ]
  },
  "package_defaults": {
    "download": {
      "kind": "huggingface_snapshot",
      "repo": "audio-cpp/audio.cpp-gguf",
      "revision": "main",
      "gated": false
    }
  },
  "packages": [
    {
      "id": "vevo2_q8_0",
      "display_name": "Vevo2 Q8_0 GGUF",
      "default": true,
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "Vevo2-GGUF",
      "files": [
        "Vevo2-GGUF/vevo2-q8_0.gguf"
      ],
      "strip_prefix": "Vevo2-GGUF"
    },
    {
      "id": "vevo2_f16",
      "display_name": "Vevo2 F16 GGUF",
      "format": "gguf",
      "precision": "f16",
      "target_directory": "Vevo2-GGUF",
      "files": [
        "Vevo2-GGUF/vevo2-f16.gguf"
      ],
      "strip_prefix": "Vevo2-GGUF"
    },
    {
      "id": "vevo2_orig",
      "display_name": "Vevo2 Original-Dtype GGUF",
      "format": "gguf",
      "precision": "orig",
      "target_directory": "Vevo2-GGUF",
      "files": [
        "Vevo2-GGUF/vevo2-orig.gguf"
      ],
      "strip_prefix": "Vevo2-GGUF"
    }
  ],
  "sources": [
    {
      "format": "gguf",
      "roots": {
        "model": ".",
        "weights": "$gguf"
      },
      "files": {
        "ar_config": "model:contentstyle_modeling/posttrained/config.json",
        "ar_amphion_config": "model:contentstyle_modeling/posttrained/amphion_config.json",
        "ar_generation_config": "model:contentstyle_modeling/posttrained/generation_config.json",
        "ar_tokenizer_config": "model:contentstyle_modeling/posttrained/tokenizer_config.json",
        "ar_tokenizer_json": "model:contentstyle_modeling/posttrained/tokenizer.json",
        "ar_vocab": "model:contentstyle_modeling/posttrained/vocab.json",
        "ar_merges": "model:contentstyle_modeling/posttrained/merges.txt",
        "ar_added_tokens": "model:contentstyle_modeling/posttrained/added_tokens.json",
        "ar_special_tokens": "model:contentstyle_modeling/posttrained/special_tokens_map.json",
        "fm_config": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa/config.json",
        "fm_text_config": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa_text/config.json",
        "vocoder_config": "model:vocoder/config.json",
        "whisper_config": "model:whisper-medium/config.json"
      },
      "tensors": {
        "content_style_tokenizer_weights": {
          "source": "weights:",
          "prefix": "content_style_tokenizer_weights"
        },
        "prosody_tokenizer_weights": {
          "source": "weights:",
          "prefix": "prosody_tokenizer_weights"
        },
        "ar_weights": {
          "source": "weights:",
          "prefix": "ar_weights"
        },
        "fm_weights": {
          "source": "weights:",
          "prefix": "fm_weights"
        },
        "fm_whisper_stats": {
          "source": "weights:",
          "prefix": "fm_whisper_stats"
        },
        "fm_text_weights": {
          "source": "weights:",
          "prefix": "fm_text_weights"
        },
        "fm_text_whisper_stats": {
          "source": "weights:",
          "prefix": "fm_text_whisper_stats"
        },
        "vocoder_weights_0": {
          "source": "weights:",
          "prefix": "vocoder_weights_0"
        },
        "vocoder_weights_1": {
          "source": "weights:",
          "prefix": "vocoder_weights_1"
        },
        "vocoder_weights_2": {
          "source": "weights:",
          "prefix": "vocoder_weights_2"
        },
        "whisper_weights": {
          "source": "weights:",
          "prefix": "whisper_weights"
        }
      }
    },
    {
      "format": "safetensors",
      "roots": {
        "model": ".",
        "whisper": "../whisper-medium"
      },
      "files": {
        "ar_config": "model:contentstyle_modeling/posttrained/config.json",
        "ar_amphion_config": "model:contentstyle_modeling/posttrained/amphion_config.json",
        "ar_generation_config": "model:contentstyle_modeling/posttrained/generation_config.json",
        "ar_tokenizer_config": "model:contentstyle_modeling/posttrained/tokenizer_config.json",
        "ar_tokenizer_json": "model:contentstyle_modeling/posttrained/tokenizer.json",
        "ar_vocab": "model:contentstyle_modeling/posttrained/vocab.json",
        "ar_merges": "model:contentstyle_modeling/posttrained/merges.txt",
        "ar_added_tokens": "model:contentstyle_modeling/posttrained/added_tokens.json",
        "ar_special_tokens": "model:contentstyle_modeling/posttrained/special_tokens_map.json",
        "fm_config": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa/config.json",
        "fm_text_config": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa_text/config.json",
        "vocoder_config": "model:vocoder/config.json",
        "whisper_config": "whisper:config.json"
      },
      "tensors": {
        "content_style_tokenizer_weights": "model:tokenizer/contentstyle_fvq16384_12.5hz/model.safetensors",
        "prosody_tokenizer_weights": "model:tokenizer/prosody_fvq512_6.25hz/model.safetensors",
        "ar_weights": "model:contentstyle_modeling/posttrained/model.safetensors",
        "fm_weights": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa/model.safetensors",
        "fm_whisper_stats": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa/whisper_stats.safetensors",
        "fm_text_weights": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa_text/model.safetensors",
        "fm_text_whisper_stats": "model:acoustic_modeling/fm_emilia101k_singnet7k_repa_text/whisper_stats.safetensors",
        "vocoder_weights_0": "model:vocoder/model.safetensors",
        "vocoder_weights_1": "model:vocoder/model_1.safetensors",
        "vocoder_weights_2": "model:vocoder/model_2.safetensors",
        "whisper_weights": "whisper:model.safetensors"
      }
    }
  ]
}