diodiogod-TTS-Audio-Suite/utils/audio_cpp/model_specs/qwen3_asr.json

{
  "family": "qwen3_asr",
  "display_name": "Qwen3-ASR",
  "description": "Qwen ASR model family for language identification and speech recognition across 30 languages, 22 Chinese dialects, and multiple English accents, with robustness for noisy, long-form, and singing audio.",
  "category": "asr",
  "status": "supported",
  "tasks": [
    "asr"
  ],
  "modes": [
    "offline",
    "streaming"
  ],
  "languages": [
    "zh",
    "en",
    "yue",
    "ar",
    "de",
    "fr",
    "es",
    "pt",
    "id",
    "it",
    "ko",
    "ru",
    "th",
    "vi",
    "ja",
    "tr",
    "hi",
    "ms",
    "nl",
    "sv",
    "da",
    "fi",
    "pl",
    "cs",
    "fil",
    "fa",
    "el",
    "hu",
    "mk",
    "ro",
    "zh dialects"
  ],
  "capabilities": {
    "asr": [
      "word_timestamps",
      "vad_chunking",
      "partial_results"
    ]
  },
  "runtime": {
    "tags": [
      "gguf",
      "stream"
    ]
  },
  "ui": {
    "recommended_package": "qwen3_asr_1_7b_q8_0",
    "tags": [
      "ASR",
      "GGUF",
      "Stream"
    ],
    "docs": [
      "docs/models/qwen3.md",
      "docs/asr.md",
      "docs/gguf.md"
    ]
  },
  "package_defaults": {
    "download": {
      "kind": "huggingface_snapshot",
      "repo": "audio-cpp/audio.cpp-gguf",
      "revision": "main",
      "gated": false
    }
  },
  "packages": [
    {
      "id": "qwen3_asr_1_7b_q8_0",
      "display_name": "Qwen3-ASR 1.7B Q8_0 GGUF",
      "default": true,
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "Qwen3-ASR-1.7B-GGUF",
      "files": [
        "Qwen3-ASR-1.7B-GGUF/qwen3-asr-1.7b-q8_0.gguf"
      ],
      "strip_prefix": "Qwen3-ASR-1.7B-GGUF"
    },
    {
      "id": "qwen3_asr_1_7b_f16",
      "display_name": "Qwen3-ASR 1.7B F16 GGUF",
      "format": "gguf",
      "precision": "f16",
      "target_directory": "Qwen3-ASR-1.7B-GGUF",
      "files": [
        "Qwen3-ASR-1.7B-GGUF/qwen3-asr-1.7b-f16.gguf"
      ],
      "strip_prefix": "Qwen3-ASR-1.7B-GGUF"
    },
    {
      "id": "qwen3_asr_0_6b_q8_0",
      "display_name": "Qwen3-ASR 0.6B Q8_0 GGUF",
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "Qwen3-ASR-0.6B-GGUF",
      "files": [
        "Qwen3-ASR-0.6B-GGUF/qwen3-asr-0.6b-q8_0.gguf"
      ],
      "strip_prefix": "Qwen3-ASR-0.6B-GGUF"
    },
    {
      "id": "qwen3_asr_0_6b_f16",
      "display_name": "Qwen3-ASR 0.6B F16 GGUF",
      "format": "gguf",
      "precision": "f16",
      "target_directory": "Qwen3-ASR-0.6B-GGUF",
      "files": [
        "Qwen3-ASR-0.6B-GGUF/qwen3-asr-0.6b-f16.gguf"
      ],
      "strip_prefix": "Qwen3-ASR-0.6B-GGUF"
    },
    {
      "id": "qwen3_asr_1_7b_safetensors",
      "display_name": "Qwen3-ASR 1.7B HF Safetensors",
      "format": "safetensors",
      "precision": "native",
      "target_directory": "Qwen3-ASR-1.7B-hf",
      "files": [
        "config.json",
        "generation_config.json",
        "model.safetensors",
        "processor_config.json",
        "tokenizer_config.json",
        "tokenizer.json"
      ],
      "download": {
        "kind": "huggingface_snapshot",
        "repo": "Qwen/Qwen3-ASR-1.7B-hf"
      }
    },
    {
      "id": "qwen3_asr_0_6b_safetensors",
      "display_name": "Qwen3-ASR 0.6B Safetensors",
      "format": "safetensors",
      "precision": "native",
      "target_directory": "Qwen3-ASR-0.6B",
      "files": [
        "config.json",
        "generation_config.json",
        "model.safetensors",
        "preprocessor_config.json",
        "tokenizer_config.json"
      ],
      "download": {
        "kind": "huggingface_snapshot",
        "repo": "Qwen/Qwen3-ASR-0.6B"
      }
    }
  ],
  "sources": [
    {
      "format": "gguf",
      "roots": {
        "model": ".",
        "weights": "$gguf"
      },
      "files": {
        "config": "model:config.json",
        "generation_config": "model:generation_config.json",
        "tokenizer_config": "model:tokenizer_config.json"
      },
      "optional_files": {
        "preprocessor_config": "model:preprocessor_config.json",
        "processor_config": "model:processor_config.json",
        "chat_template": "model:chat_template.json",
        "chat_template_jinja": "model:chat_template.jinja",
        "vocab": "model:vocab.json",
        "merges": "model:merges.txt",
        "tokenizer_json": "model:tokenizer.json"
      },
      "tensors": {
        "weights": "weights:"
      }
    },
    {
      "format": "safetensors",
      "roots": {
        "model": "."
      },
      "files": {
        "config": "model:config.json",
        "generation_config": "model:generation_config.json",
        "tokenizer_config": "model:tokenizer_config.json"
      },
      "optional_files": {
        "preprocessor_config": "model:preprocessor_config.json",
        "processor_config": "model:processor_config.json",
        "chat_template": "model:chat_template.json",
        "chat_template_jinja": "model:chat_template.jinja",
        "vocab": "model:vocab.json",
        "merges": "model:merges.txt",
        "tokenizer_json": "model:tokenizer.json"
      },
      "tensors": {
        "weights": "model:model.safetensors"
      }
    }
  ]
}