{ "audio_end_token": "<|audio_end|>", "audio_start_token": "<|audio_start|>", "audio_token": "<|AUDIO_PAD|>", "chunk_length": 30, "discrete_audio_end_token": "<|discrete_audio_end|>", "discrete_audio_start_token": "<|discrete_audio_start|>", "discrete_audio_token": "<|DISCRETE_AUDIO_PAD|>", "feature_extractor_type": "WhisperFeatureExtractor", "feature_size": 128, "hop_length": 160, "n_fft": 400, "n_samples": 480000, "nb_max_frames": 3000, "padding_side": "right", "padding_value": 0.0, "processor_class": "Qwen2AudioProcessor", "return_attention_mask": true, "sampling_rate": 16000, "use_discrete_token": false }