138 lines
4.7 KiB
JSON
138 lines
4.7 KiB
JSON
{
|
|
"default_model": "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online",
|
|
"hotword_model": "iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
|
|
"models": {
|
|
"iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online": {
|
|
"alias": "paraformer-zh-streaming",
|
|
"directory": "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online",
|
|
"description": "FunASR 流式 Paraformer 语音识别模型，用于实时首遍识别并输出中间结果",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"config.yaml"
|
|
],
|
|
"any_files": [
|
|
"*.pb",
|
|
"*.pt",
|
|
"*.onnx",
|
|
"*.bin",
|
|
"*.model",
|
|
"*.safetensors"
|
|
],
|
|
"min_total_size_bytes": 1000000
|
|
},
|
|
"iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404": {
|
|
"alias": "paraformer-zh-contextual",
|
|
"directory": "iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
|
|
"description": "FunASR Contextual Paraformer 热词模型，用于结合会话热词生成最终识别结果",
|
|
"revision": "v2.0.4",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"config.yaml"
|
|
],
|
|
"any_files": [
|
|
"*.pt",
|
|
"*.bin",
|
|
"*.safetensors"
|
|
],
|
|
"min_total_size_bytes": 1000000
|
|
}
|
|
},
|
|
"auxiliary_models": {
|
|
"damo/speech_fsmn_vad_zh-cn-16k-common-pytorch": {
|
|
"alias": "vad",
|
|
"directory": "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
|
|
"kind": "vad",
|
|
"description": "FSMN 语音活动检测模型，用于检测语音起止并切分语音片段",
|
|
"revision": "v2.0.2",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"config.yaml",
|
|
"model.pb"
|
|
],
|
|
"min_total_size_bytes": 1000000,
|
|
"funasr_alias": "fsmn-vad"
|
|
},
|
|
"iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch": {
|
|
"alias": "ct-punc",
|
|
"directory": "iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
|
|
"kind": "punctuation",
|
|
"description": "CT-Transformer 标点恢复模型，用于为识别文本补充标点符号（可选）",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"config.yaml"
|
|
],
|
|
"any_files": [
|
|
"*.pt",
|
|
"*.bin",
|
|
"*.onnx"
|
|
],
|
|
"min_total_size_bytes": 1000000
|
|
},
|
|
"iic/speech_campplus_speaker-diarization_common": {
|
|
"alias": "diarization",
|
|
"directory": "iic/speech_campplus_speaker-diarization_common",
|
|
"kind": "diarization",
|
|
"description": "CAM++ 音视频说话人分离扩展包，包含音频检测及人脸关联所需组件",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"config.yaml",
|
|
"onnx/asd.onnx",
|
|
"onnx/face_recog_ir101.onnx",
|
|
"onnx/fqa.onnx",
|
|
"onnx/version-RFB-320.onnx"
|
|
],
|
|
"min_total_size_bytes": 50000000
|
|
},
|
|
"iic/speech_campplus_sv_zh-cn_16k-common": {
|
|
"alias": "speaker",
|
|
"directory": "iic/speech_campplus_sv_zh-cn_16k-common",
|
|
"kind": "speaker_verification",
|
|
"description": "CAM++ 声纹特征模型，用于提取说话人向量并进行会话内说话人匹配",
|
|
"revision": "v2.0.2",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"config.yaml",
|
|
"campplus_cn_common.bin"
|
|
],
|
|
"min_total_size_bytes": 10000000
|
|
},
|
|
"iic/speech_eres2netv2_sv_zh-cn_16k-common": {
|
|
"alias": "realtime-speaker",
|
|
"directory": "iic/speech_eres2netv2_sv_zh-cn_16k-common",
|
|
"kind": "realtime_speaker_verification",
|
|
"description": "ERes2NetV2 实时声纹验证模型，用于提取和比对说话人特征",
|
|
"required_files": [
|
|
"configuration.json"
|
|
],
|
|
"any_files": [
|
|
"*"
|
|
],
|
|
"min_total_size_bytes": 10000000
|
|
},
|
|
"damo/speech_campplus_sv_zh-cn_16k-common": {
|
|
"alias": "speaker-damo",
|
|
"directory": "damo/speech_campplus_sv_zh-cn_16k-common",
|
|
"kind": "speaker_verification",
|
|
"description": "CAM++ 声纹验证模型资源，供相关说话人识别配置使用",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"config.yaml",
|
|
"campplus_cn_common.bin"
|
|
],
|
|
"min_total_size_bytes": 10000000
|
|
},
|
|
"damo/speech_campplus-transformer_scl_zh-cn_16k-common": {
|
|
"alias": "speaker-transformer",
|
|
"directory": "damo/speech_campplus-transformer_scl_zh-cn_16k-common",
|
|
"kind": "speaker_transformer",
|
|
"description": "CAM++ 说话人聚类的 Transformer/SCL 辅助权重，需与声纹模型配套使用",
|
|
"required_files": [
|
|
"configuration.json",
|
|
"campplus_cn_encoder.pt",
|
|
"transformer_backend.pt"
|
|
],
|
|
"min_total_size_bytes": 10000000
|
|
}
|
|
}
|
|
}
|