| { | |
| "model_type": "prosody_to_text", | |
| "architectures": [ | |
| "ProsodyToTextModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_prosody.ProsodyToTextConfig", | |
| "AutoModel": "modeling_prosody.ProsodyToTextModel" | |
| }, | |
| "mel_bins": 12, | |
| "length_ratio": 0.5, | |
| "feature_rate_hz": 200.0, | |
| "f0_scale": 500.0, | |
| "intensity_scale": 100.0, | |
| "whisper_subfolder": "whisper", | |
| "tokenizer_subfolder": "tokenizer", | |
| "num_beams": 10, | |
| "language": "en", | |
| "no_repeat_ngram_size": 3, | |
| "max_new_tokens": 225, | |
| "conformer_subfolder": "conformer", | |
| "constrain": true | |
| } | |