[src/libmpg123/parse.c:wetwork():1365] error: Giving up resync after 1024 bytes

[qianqianque163645546464]

❓ Questions and Help

The code runtime reported the following error

Note: Illegal Audio-MPEG-Header 0x68746d6c at offset 584064. Note: Trying to resync... Note: Skipped 1024 bytes in input. [src/libmpg123/parse.c:wetwork():1365] error: Giving up resync after 1024 bytes - your stream is not nice... (maybe increasing resync limit could help). Traceback (most recent call last): File "/home/wangyu/Disk/tools/vllm-gptq/tests/qwen/zheng_qwen_0311.py", line 25, in res = model.generate(input=f"{model.model_path}/example/test06.wav", File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 206, in generate return self.inference(input, input_len=input_len, **cfg) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 240, in inference results, meta_data = model.inference(**batch, **kwargs) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/funasr/models/bicif_paraformer/model.py", line 247, in inference audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000)) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/funasr/utils/load_utils.py", line 34, in load_audio_text_image_video return [load_audio_text_image_video(audio, fs=fs, audio_fs=audio_fs, data_type=data_type, **kwargs) for audio in data_or_path_or_list] File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/funasr/utils/load_utils.py", line 34, in return [load_audio_text_image_video(audio, fs=fs, audio_fs=audio_fs, data_type=data_type, **kwargs) for audio in data_or_path_or_list] File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/funasr/utils/load_utils.py", line 41, in load_audio_text_image_video data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/torchaudio/_backend/utils.py", line 205, in load return backend.load(uri, frame_offset, num_frames, normalize, channels_first, format, buffer_size) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/torchaudio/_backend/soundfile.py", line 27, in load return soundfile_backend.load(uri, frame_offset, num_frames, normalize, channels_first, format) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/torchaudio/backend/soundfile_backend.py", line 230, in load waveform = file.read(frames, dtype, always_2d=True) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/soundfile.py", line 895, in read frames = self._array_io('read', out, frames) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/soundfile.py", line 1344, in _array_io return self._cdata_io(action, cdata, ctype, frames) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/soundfile.py", line 1354, in _cdata_io _error_check(self._errorcode) File "/home/wangyu/miniconda3/envs/pinpan/lib/python3.10/site-packages/soundfile.py", line 1407, in _error_check raise LibsndfileError(err, prefix=prefix) soundfile.LibsndfileError: Unspecified internal error. 0%| | 0/2 [00:00<?, ?it/s]

code

from funasr import AutoModel model = AutoModel(model="/home/wangyu/Disk/tools/Moda-shengwen/", ） res = model.generate(input=f"{model.model_path}/example/test06.wav", )

This audio is in WAV format and can be played. It can be transcribed normally using Whispe Large v3. Does anyone know the reason for this?

• OS (Linux):
• FunASR Version 1.0.0:
• ModelScope Version 1.11.0:

[Adenialzz]

Hi, have you solved this?