drewThomasson

/

Morgan_freeman_xtts_model

like 1

Yeah

I know

Morgan freeman is really hard to train for

He’s never read any books

And a lot of his lines are almost whisper like :/

Hey,

Is anyone using this model with Coqui? I am trying to get it to run on my Docker instance with the CPU....

mike@plexy:~/Docker/coqui$ docker exec -it workingTTS bash

mike@plexy:~/Docker/coqui/models/MorganFreedman$ docker exec -it workingTTS bash

root@76ff1f38da5c:~# python TTS/server/server.py --model_path /models/MorganFreedman --config_path /models/MorganFreedman
Traceback (most recent call last):
File "/root/TTS/server/server.py", line 104, in
synthesizer = Synthesizer(
File "/root/TTS/utils/synthesizer.py", line 93, in init
self._load_tts(tts_checkpoint, tts_config_path, use_cuda)
File "/root/TTS/utils/synthesizer.py", line 183, in _load_tts
self.tts_config = load_config(tts_config_path)
File "/root/TTS/config/init.py", line 94, in load_config
raise TypeError(f" [!] Unknown config file type {ext}")
TypeError: [!] Unknown config file type

I changed the JSON.config file to disable CUDA and that didn't seem to help.

mike@plexy:~/Docker/coqui/models/MorganFreedman$ grep cudnn *
config.json: "cudnn_enable": false,

no idea I would ask Coqui

also make sure your looking at the active coqui, the company died and you need to be using the fork thats kept alive by the community

https://github.com/idiap/coqui-ai-TTS

Thanks. There were several forks of the project... I'll give this one a try...

Thanks. Love ebook2audiobook.

🫶