White page on gradio.live when launched via colab notebook #330

New Issue

ziengri · 2023-08-17T14:01:11Z

ziengri commented

2023-08-17 14:01:11 +00:00

I'm launching it ./start.sh --share, in google collab, everything seems to be normal, but when you go to the link from gradio, a white page comes out.
There are also two errors:

Error: No module named 'vall_e'
Error: No module named 'bark'

Log ./start.sh

/content/ai-voice-cloning
./start.sh: line 3: ./venv/bin/activate: No such file or directory
Whisper detected
Error: No module named 'vall_e'
Error: No module named 'bark'
Downloading autoregressive.pth from https://huggingface.co/jbetker/tortoise-tts-v2/resolve/main/.models/autoregressive.pth...
Done.
Downloading diffusion_decoder.pth from https://huggingface.co/jbetker/tortoise-tts-v2/resolve/main/.models/diffusion_decoder.pth...
Done.
Running on local URL:  http://127.0.0.1:7860
Running on public URL: https://fd3ba90c3bed8e57f4.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
Loading TorToiSe... (AR: None, diffusion: None, vocoder: bigvgan_24khz_100band)
Hardware acceleration found: cuda
Loading tokenizer JSON: /content/ai-voice-cloning/modules/tortoise-tts/tortoise/../tortoise/data/tokenizer.json
Loaded tokenizer
Loading autoregressive model: /content/ai-voice-cloning/models/tortoise/autoregressive.pth
Loaded autoregressive model
Loaded diffusion model
Done.
Loading vocoder model: bigvgan_24khz_100band
Done.
Loading vocoder model: bigvgan_24khz_100band.pth
Done.
Removing weight norm...
Loaded vocoder model
Loaded TTS, ready for generation.
websocket: server started

I'm launching it ./start.sh --share, in google collab, everything seems to be normal, but when you go to the link from gradio, a white page comes out. There are also two errors: ``` Error: No module named 'vall_e' Error: No module named 'bark' ``` Log ./start.sh ``` /content/ai-voice-cloning ./start.sh: line 3: ./venv/bin/activate: No such file or directory Whisper detected Error: No module named 'vall_e' Error: No module named 'bark' Downloading autoregressive.pth from https://huggingface.co/jbetker/tortoise-tts-v2/resolve/main/.models/autoregressive.pth... Done. Downloading diffusion_decoder.pth from https://huggingface.co/jbetker/tortoise-tts-v2/resolve/main/.models/diffusion_decoder.pth... Done. Running on local URL: http://127.0.0.1:7860 Running on public URL: https://fd3ba90c3bed8e57f4.gradio.live This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces Loading TorToiSe... (AR: None, diffusion: None, vocoder: bigvgan_24khz_100band) Hardware acceleration found: cuda Loading tokenizer JSON: /content/ai-voice-cloning/modules/tortoise-tts/tortoise/../tortoise/data/tokenizer.json Loaded tokenizer Loading autoregressive model: /content/ai-voice-cloning/models/tortoise/autoregressive.pth Loaded autoregressive model Loaded diffusion model Done. Loading vocoder model: bigvgan_24khz_100band Done. Loading vocoder model: bigvgan_24khz_100band.pth Done. Removing weight norm... Loaded vocoder model Loaded TTS, ready for generation. websocket: server started ```

Sign in to join this conversation.