funasr/datasets/audio_datasets/update_jsonl.py
@@ -50,8 +50,8 @@ sample_num = len(waveform) source_len = int(sample_num / 16000 * 1000 / 10) source_len_old = data["source_len"] if source_len_old != source_len: print(f"wav: {wav_path}, old: {source_len_old}, new: {source_len}") if (source_len_old - source_len) > 100 or (source_len - source_len_old) > 100: print(f"old: {source_len_old}, new: {source_len}, wav: {wav_path}") data["source_len"] = source_len jsonl_line = json.dumps(data, ensure_ascii=False) lines[i] = jsonl_line
