You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
hey @acastry did you try deploying this in GPU-based instance? melo_server and whisper_server require GPU instances as mentioned in their docker config.
Hello there is a fatal error when trying to deploy whisper-melo-llama3
First it is necessary to modify bolna_server.Dockerfile to get the last repository right ?
RUN pip install --force-reinstall git+https://github.com/bolna-ai/bolna@MeloTTS
to:
RUN pip install --force-reinstall git+https://github.com/bolna-ai/bolna@master
Then the fatal error i guess in MeloTTS :
` => [melo-app 5/10] RUN git clone https://github.com/bolna-ai/MeloTTS 2.1s
=> [melo-app 6/10] RUN pip install fastapi uvicorn torchaudio 46.9s
=> [bolna-app 12/14] RUN pip install pydub==0.25.1 1.6s
=> [bolna-app 13/14] RUN pip install ffprobe 2.7s
=> [bolna-app 14/14] RUN pip install aiofiles 1.3s
=> ERROR [bolna-app] exporting to docker image format 183.9s
=> => exporting layers 112.2s
=> => exporting manifest sha256:06c40a005b2f6040981b04d677a5994fa440a4b8b0a826bb7193ffae940856e5 0.0s
=> => exporting config sha256:89c37bae6f62aca0d4d57689610467537971fa097ea12c00147f3fc21cd900d5 0.0s
=> => sending tarball 71.7s
=> [melo-app 7/10] RUN cp -a MeloTTS/. . 0.7s
=> [melo-app 8/10] RUN python -m pip cache purge 0.8s
=> ERROR [melo-app 9/10] RUN pip install --no-cache-dir txtsplit torch torchaudio cached_path transformers==4.27.4 mecab-python3==1.0.5 num2words==0.5.12 unidic_lite unidic mecab-python3==1.0.5 pykaka 147.7s
=> [whisper-app 9/12] RUN pip install git+https://github.com/SYSTRAN/faster-whisper.git 8.6s
=> [whisper-app 10/12] RUN pip install transformers 11.1s
=> [whisper-app 11/12] RUN ct2-transformers-converter --model openai/whisper-small --copy_files preprocessor_config.json --output_dir ./Server/ASR/whisper_small --quantization float16 33.0s
=> [whisper-app 12/12] WORKDIR Server 0.0s
=> CANCELED [whisper-app] exporting to docker image format 87.4s
=> => exporting layers 87.4s
=> CANCELED [bolna-app bolna-app] importing to docker 17.5s
failed to solve: process "/bin/sh -c pip install --no-cache-dir txtsplit torch torchaudio cached_path transformers==4.27.4 mecab-python3==1.0.5 num2words==0.5.12 unidic_lite unidic mecab-python3==1.0.5 pykakasi==2.2.1 fugashi==1.3.0 g2p_en==2.1.0 anyascii==0.3.2 jamo==0.4.1 gruut[de,es,fr]==2.2.3 g2pkk>=0.1.1 librosa==0.9.1 pydub==0.25.1 eng_to_ipa==0.0.2 inflect==7.0.0 unidecode==1.3.7 pypinyin==0.50.0 cn2an==0.5.22 jieba==0.42.1 langid==1.1.6 tqdm tensorboard==2.16.2 loguru==0.7.2" did not complete successfully: exit code: 1
`
Thanks for your support,
The text was updated successfully, but these errors were encountered: