| name: whisper_speech_recognition | |
| config_type: model | |
| vocab_size: 51865 | |
| num_mel_bins: 80 | |
| encoder_layers: 12 | |
| encoder_attention_heads: 12 | |
| decoder_layers: 12 | |
| decoder_attention_heads: 12 | |
| num_hidden_layers: 12 | |
| decoder_ffn_dim: 3072 | |
| encoder_ffn_dim: 3072 | |
| encoder_layerdrop: 0.0 | |
| decoder_layerdrop: 0.0 | |
| decoder_start_token_id: 50258 | |
| use_cache: false | |
| sampling_rate: 16000 | |
| is_encoder_decoder: true | |
| activation_function: gelu | |
| d_model: 768 | |
| dropout: 0.0 | |
| torch_dtype: float32 | |
| attention_dropout: 0.0 | |
| activation_dropout: 0.0 | |
| init_std: 0.02 | |
| scale_embedding: false | |
| max_source_positions: 1500 | |
| max_target_positions: 448 | |
| pad_token_id: 50257 | |
| bos_token_id: 50257 | |
| eos_token_id: 50257 | |
| suppress_tokens: [] | |
| begin_suppress_tokens: | |
| - 220 | |
| - 50257 | |
| use_weighted_layer_sum: false | |
| classifier_proj_size: 256 | |
| apply_spec_augment: false | |
| mask_time_prob: 0.05 | |
| mask_time_length: 10 | |
| mask_time_min_masks: 2 | |
| mask_feature_prob: 0.0 | |
| mask_feature_length: 10 | |
| mask_feature_min_masks: 0 | |
| max_new_tokens: 444 | |
| generation_config: | |
| alignment_heads: null | |
| begin_suppress_tokens: [220, 50256] | |
| bos_token_id: 50257 | |
| decoder_start_token_id: 50258 | |
| eos_token_id: 50257 | |
| forced_decoder_ids: [[1, None], [2, 50359]] | |
| is_multilingual: True | |
| max_initial_timestamp_index: 50 | |
| max_length: 448 | |
| max_new_tokens: 444 | |
| no_timestamps_token_id: 50363 | |
| pad_token_id: 50257 | |
| prev_sot_token_id: 50361 | |
| return_timestamps: false | |
| suppress_tokens: null | |
| task_to_id: | |
| transcribe: 50359 | |
| translate: 50358 | |