| { | |
| "sampling_rate": 16000, | |
| "n_fft": 400, | |
| "hop_length": 160, | |
| "n_mels": 80, | |
| "d_model": 384, | |
| "n_heads": 6, | |
| "n_layers": 4, | |
| "vocab_size": 1000, | |
| "batch_size": 16, | |
| "learning_rate": 0.0003, | |
| "weight_decay": 0.01, | |
| "max_epochs": 20, | |
| "warmup_steps": 1000, | |
| "grad_clip": 1.0, | |
| "max_audio_length": 30.0, | |
| "max_text_length": 448, | |
| "data_dir": "./whisper/data", | |
| "checkpoint_dir": "./whisper/checkpoints", | |
| "tensorboard_dir": "./whisper/logs", | |
| "model_type": "whisper", | |
| "transformers_version": "4.30.0", | |
| "architectures": [ | |
| "WhisperForConditionalGeneration" | |
| ], | |
| "use_cache": true, | |
| "encoder_attention_heads": 6, | |
| "decoder_attention_heads": 6, | |
| "encoder_layers": 4, | |
| "decoder_layers": 4, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "decoder_ffn_dim": 1536, | |
| "encoder_ffn_dim": 1536, | |
| "activation_function": "gelu", | |
| "num_mel_bins": 80, | |
| "pad_token_id": 0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "suppress_tokens": [], | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ] | |
| } |