funasr/datasets/audio_datasets/datasets.py
@@ -58,7 +58,7 @@ data_src = load_audio_text_image_video(source, fs=self.fs) if self.preprocessor_speech: data_src = self.preprocessor_speech(data_src) speech, speech_lengths = extract_fbank(data_src, data_type=self.data_type, frontend=self.frontend) # speech: [b, T, d] speech, speech_lengths = extract_fbank(data_src, data_type=self.data_type, frontend=self.frontend, is_final=True) # speech: [b, T, d] target = item["target"] if self.preprocessor_text:
