Camb-ai / MARS5-TTS

MARS5 speech model (TTS) from CAMB.AI
https://www.camb.ai
GNU Affero General Public License v3.0
1.37k stars 95 forks source link

mars5_demo in Collab issue #27

Closed PS-AI closed 1 week ago

PS-AI commented 1 week ago

The output audio is not synthesized.

akshhack commented 1 week ago

Hey @PS-AI it has been working well for quite a few people -- can you please help me understand your problem a bit better.

Adibian commented 1 week ago

Hi @akshhack I have the same problem. I just ran your Collb code but 9 seconds of silence is synthesized! Also, it lasted a long time to synthesize it (I don't know if it is normal or not for MARS5)

test

pieterscholtz commented 1 week ago

@PS-AI @Adibian We've merged a fix for this. For it to take effect, you may need to delete your torch hub cache before trying it again, e.g.: rm -rf ~/.cache/torch/hub/Camb-ai_mars5-tts_master Or simply add force_reload=True to torch.hub.load call. Please note that this is a CPU only bug and that inference on CPU will be quite slow.