WIP

config.json

@@ -1 +1 @@
-{"vocab_size": 32, "num_mel_bins": 80, "d_model": 384, "encoder_layers": 4, "encoder_attention_heads": 6, "decoder_layers": 4, "decoder_attention_heads": 6, "decoder_ffn_dim": 1536, "encoder_ffn_dim": 1536, "dropout": 0.0, "attention_dropout": 0.0, "activation_dropout": 0.0, "activation_function": "gelu", "init_std": 0.02, "encoder_layerdrop": 0.0, "decoder_layerdrop": 0.0, "use_cache": true, "num_hidden_layers": 4, "scale_embedding": false, "max_source_positions": 1500, "max_target_positions": 448, "classifier_proj_size": 256, "use_weighted_layer_sum": false, "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, "median_filter_width": 7, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": true, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [0, 1, 2], "architectures": ["WhisperForConditionalGeneration"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.38.2", "model_type": "whisper"}
+{"vocab_size": 32, "num_mel_bins": 80, "d_model": 384, "encoder_layers": 4, "encoder_attention_heads": 6, "decoder_layers": 4, "decoder_attention_heads": 6, "decoder_ffn_dim": 1536, "encoder_ffn_dim": 1536, "dropout": 0.0, "attention_dropout": 0.0, "activation_dropout": 0.0, "activation_function": "gelu", "init_std": 0.02, "encoder_layerdrop": 0.0, "decoder_layerdrop": 0.0, "use_cache": true, "num_hidden_layers": 4, "scale_embedding": false, "max_source_positions": 1500, "max_target_positions": 448, "classifier_proj_size": 256, "use_weighted_layer_sum": false, "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, "median_filter_width": 7, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": true, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [0, 1, 2], "architectures": ["WhisperForConditionalGeneration"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": 1, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.38.2", "model_type": "whisper"}