-
The issue I'm experiencing is very similar to what’s described here ("hoarseness" when reaching for higher notes). You can listen to samples in the link below:
https://github.com/coqui-ai/TTS/issues/…
-
New thread as its a different issue this time.
So I load the webui,
Click on train
In finetune model name I write commentator
I drop my audio sample ont the audio input section and wait for it…
-
Traceback (most recent call last):
File "#Redacted#\xtts-webui\app.py", line 67, in
from xtts_webui import demo
File "#Redacted#\xtts-webui\xtts_webui.py", line 97, in
import modules…
-
**🚀 Feature Description**
faster laod at startup
12sec and i use an NVSSD with 2GB/sec
**Solution**
leave unnessesary compling , checking, hash generation, save for next session ?!?
**Addit…
-
Loading model...
Computing speaker latents...
!!! Exception during processing!!! Invalid file: {'waveform': tensor([[[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.]]]), 'sample_rate': …
-
i updated to v 2.4.6, isntall was succesfull on ubuntu 22.04 WSL
after that, the same command that was still working yesterday fails with taht error:
Installing collected packages: epub2tts
…
-
```
@app.post("/api/xtts_stream")
def gpt_xtts_stream(inputs: xtts_stream_inputs):
try:
speaker["text"] = inputs.text
speaker['language'] = inputs.language
speaker['s…
-
Hi, I want to train your XTTS-v2 in distributed mode since my data is too large. How can I do that ? thank you!!!
-
To create a public link, set `share=True` in `launch()`.
hello world
Traceback (most recent call last):
File "S:\Ai\Audio-AI\xtts-webui\venv\lib\site-packages\gradio\queueing.py", line 489, in ca…
-
**LocalAI version:** 2.15.0
Docker: image: quay.io/go-skynet/local-ai:master-cublas-cuda12-ffmpeg
**Environment, CPU architecture, OS, and Version:**
Ubuntu 22.04 GPU
**Describe the bug**…