| { | |
| "feature_extractor_type": "MingV3ASRFeatureExtractor", | |
| "processor_class": "MingV3ASRProcessor", | |
| "feature_size": 128, | |
| "sampling_rate": 16000, | |
| "padding_value": 0.0, | |
| "audio_config": { | |
| "n_mels": 128, | |
| "n_audio_ctx": 3000, | |
| "n_audio_state": 1280, | |
| "n_audio_head": 20, | |
| "n_audio_layer": 32, | |
| "downsampler_kernel_size_list": [ | |
| 3 | |
| ], | |
| "downsampler_stride_list": [ | |
| 2 | |
| ], | |
| "chunk_frames": 3000, | |
| "downsampler_padding_list": [ | |
| 1 | |
| ] | |
| }, | |
| "auto_map": { | |
| "AutoFeatureExtractor": "feature_extraction_ming_v3_asr.MingV3ASRFeatureExtractor", | |
| "AutoProcessor": "processing_ming_v3_asr.MingV3ASRProcessor" | |
| } | |
| } | |