{ "_name_or_path": "Salama1429/KalemaTech-Arabic-STT-ASR-based-on-Whisper-Small", "activation_dropout": 0.0, "activation_function": "gelu", "apply_spec_augment": false, "architectures": [ "WhisperForConditionalGeneration" ], "attention_dropout": 0.0, "begin_suppress_tokens": null, "bos_token_id": 50257, "classifier_proj_size": 256, "d_model": 768, "decoder_attention_heads": 12, "decoder_ffn_dim": 3072, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 50258, "dropout": 0.0, "encoder_attention_heads": 12, "encoder_ffn_dim": 3072, "encoder_layerdrop": 0.0, "encoder_layers": 12, "eos_token_id": 50257, "forced_decoder_ids": null, "init_std": 0.02, "is_encoder_decoder": true, "mask_feature_length": 10, "mask_feature_min_masks": 0, "mask_feature_prob": 0.0, "mask_time_length": 10, "mask_time_min_masks": 2, "mask_time_prob": 0.05, "max_length": null, "max_source_positions": 1500, "max_target_positions": 448, "median_filter_width": 7, "model_type": "whisper", "num_hidden_layers": 12, "num_mel_bins": 80, "pad_token_id": 50257, "scale_embedding": false, "torch_dtype": "float32", "transformers_version": "4.45.2", "use_cache": false, "use_weighted_layer_sum": false, "vocab_size": 51865 }