ASR cannot working

[SimpleJoeie]

trafficstars

Running on local URL: http://0.0.0.0:9874 "/opt/miniconda3/envs/GPTSoVits/bin/python" tools/asr/fasterwhisper_asr.py -i "output/denoise_opt" -o "output/asr_opt" -s large-v3 -l ja -p float32 loading faster whisper model: large-v3 large-v3 0%| | 0/10 [00:00<?, ?it/s]/opt/miniconda3/envs/GPTSoVits/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d ' "/opt/miniconda3/envs/GPTSoVits/bin/python" tools/asr/fasterwhisper_asr.py -i "./output/denoise_opt" -o "output/asr_opt" -s large-v3 -l ja -p float32 loading faster whisper model: large-v3 large-v3 0%| | 0/10 [00:00<?, ?it/s]/opt/miniconda3/envs/GPTSoVits/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d ' "/opt/miniconda3/envs/GPTSoVits/bin/python" tools/asr/fasterwhisper_asr.py -i "./output/denoise_opt" -o "output/asr_opt" -s small -l ja -p float32 loading faster whisper model: small small config.json: 2.37kB [00:00, 371kB/s]
vocabulary.txt: 460kB [00:00, 788kB/s] tokenizer.json: 2.20MB [00:00, 2.45MB/s] | 0.00/484M [00:00<?, ?B/s] model.bin: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 484M/484M [20:37<00:00, 391kB/s] 10%|██████████████▎ | 1/10 [00:04<00:41, 4.59s/it]/opt/miniconda3/envs/GPTSoVits/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '

[SimpleJoeie]

macos 12.6.3 intel ffmpeg 7.0

[XXXXRT666]

没看到报错，如果明确是warning导致的问题可以环境变量关闭这个warning

[SapphireLab]

did you install the miniconda in x86_64 way? check your conda-info info if x86_64, it may cause problem in CTtranslated2 to stop the faster whisper.

[XXXXRT666]

did you install the miniconda in x86_64 way? check your conda-info info

if x86_64, it may cause problem in CTtranslated2 to stop the faster whisper.

I think Intel Mac is X86_64, anyway,only macOS Sonoma support FFT, so there will be some error while training

[xtopass]

达摩的ASR 下载出现了问题。有人和我出现了同样的问题吗？需要怎样解决

[SapphireLab]

达摩的ASR 下载出现了问题。有人和我出现了同样的问题吗？需要怎样解决

换个网络吧，能上modelscope的话直接访问然后下载也可以. 可能是api不太对劲.

[XXXXRT666]

https://github.com/SYSTRAN/faster-whisper/issues/345 this might help

[etdapt]

I have been facing same issue... I debug-stepped through fasterwhisper_asr.py and found that it is failing while looping through the segments returned from mode.transcribe()

Running on local URL: http://0.0.0.0:9874 "/opt/miniconda3/envs/GPTSoVits/bin/python" tools/asr/fasterwhisper_asr.py -i "output/denoise_opt" -o "output/asr_opt" -s large-v3 -l ja -p float32 loading faster whisper model: large-v3 large-v3 0%| | 0/10 [00:00<?, ?it/s]/opt/miniconda3/envs/GPTSoVits/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d ' "/opt/miniconda3/envs/GPTSoVits/bin/python" tools/asr/fasterwhisper_asr.py -i "./output/denoise_opt" -o "output/asr_opt" -s large-v3 -l ja -p float32 loading faster whisper model: large-v3 large-v3 0%| | 0/10 [00:00<?, ?it/s]/opt/miniconda3/envs/GPTSoVits/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d ' "/opt/miniconda3/envs/GPTSoVits/bin/python" tools/asr/fasterwhisper_asr.py -i "./output/denoise_opt" -o "output/asr_opt" -s small -l ja -p float32 loading faster whisper model: small small config.json: 2.37kB [00:00, 371kB/s] vocabulary.txt: 460kB [00:00, 788kB/s] tokenizer.json: 2.20MB [00:00, 2.45MB/s] | 0.00/484M [00:00<?, ?B/s] model.bin: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 484M/484M [20:37<00:00, 391kB/s] 10%|██████████████▎ | 1/10 [00:04<00:41, 4.59s/it]/opt/miniconda3/envs/GPTSoVits/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '

[RVC-Boss]

达摩的ASR 下载出现了问题。有人和我出现了同样的问题吗？需要怎样解决

他这个每格可能有好几百M，比如你全下完了甚至下了一半才会更新一个超长的大格。所以应该只是下得慢？

[xtopass]

他这个每格可能有好几百M，比如你全下完了甚至下了一半才会更新一个超长的大格。所以应该只是下得慢？ 多谢回复，我挂了几个小时，没有进度。一个840M大小的文件

[xtopass]

达摩的ASR 下载出现了问题。有人和我出现了同样的问题吗？需要怎样解决

换个网络吧，能上modelscope的话直接访问然后下载也可以. 可能是api不太对劲. modelscope能直连，我感觉也是。

[xtopass]

今天已经下载好了！关于FSR的文件