search

open-mmlab / Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
https://openhlt.github.io/amphion/
MIT License
4.45k stars 379 forks source link

[Help]: inference the model of vall-e report error #134

Closed fangbingxiao closed 5 months ago

fangbingxiao commented 7 months ago

the report error is :

subprocess.CalledProcessError: Command '['/data/gpu_env_common/env/anaconda3/envs/whisper_valle_fang/bin/python3.9', '/data/bingxiao.fang/txt_to_speech/Amphion/bins/tts/inference.py', '--config', 'ckpts/tts/valle_libritts/args.json', '--log_level', 'debug', '--acoustics_dir', 'ckpts/tts/valle_libritts', '--output_dir', 'ckpts/tts/valle_libritts/result', '--mode', 'single', '--text', 'This is a clip of generated speech with the given text from Amphion Vall-E model.', '--text_prompt', 'But even the unsuccessful dramatist has his moments.', '--audio_prompt', 'egs/tts/VALLE/prompt_examples/7176_92135_000004_000000.wav', '--test_list_file', 'None']' died with <Signals.SIGSEGV: 11>.

HarryHe11 commented 7 months ago

Hi @fangbingxiao, thank you for bringing this issue to our attention. However, the error information provided is a bit too vague for us to offer effective assistance. Could you please share a more detailed error traceback and some context about your experiment?

lmxue commented 6 months ago

Hi @fangbingxiao, my friend also encountered this problem yesterday. She sent me the log and I checked it.

A SIGSEGV signal, represented by <Signals.SIGSEGV: 11>, indicates a segmentation fault has occurred. This is a type of error caused by a program trying to read or write an illegal memory location. It's a common critical error that leads to a program crash.

Therefore, you can check if there's enough memory available on your system. Insufficient memory might lead to segmentation faults, especially when working with large models or datasets.

RMSnow commented 5 months ago

Hi @fangbingxiao, if you have any further questions, feel free to re-open this issue. We are glad to follow up!