-
请问有在中文数据上训的对应这500个中文unit的vocoder吗
-
Thank you for this great work!
I successfully trained on my custom dataset for another language. In the saved checkpoints folder, I see all checkpoints, including the last.ckpt. To sysnthesize spee…
-
### Checks
- [X] This template is only for question, not feature requests or bug reports.
- [X] I have thoroughly reviewed the project documentation and read the related paper(s).
- [X] I have search…
-
The title pretty much explains the problem
I have no idea what could be causing this problem
-
I first run the "python -m omni_speech.serve.model_worker --host myIP --controller http://myIP:10000 --port 40000 --worker http://myIP:40000 --model-path Llama-3.1-8B-Omni --model-name Llama-3.1-8B-Om…
-
如果挂梯子就会快速跳过,如果不挂梯子就会卡在Download Vocos from huggingface charactr/vocos-mel-24khz,超时跳过,极大拖慢了配音速度
INFO:__main__:Accessing generate_audio route
INFO:__main__:Processing audio file: audio
Download Vocos …
-
If I usa another sampling rate like 16kHz, how should I train the new vocoder?
-
# Goal
Replace existing TTS cascade with a speech decoder that directly generates speech. This change will replace the current TTS cascade which adds latency to ichigo's response time.
# Potential So…
-
Description:
I converted the decoder of a TTS model (with HiFi-GAN vocoder) from PyTorch to ONNX and then to an engine format. During inference, both input and output shapes are dynamic, changing wit…
-
I'd like to be able to:
1) Change the pitch of a sample without speeding it up or slowing it down. It seems the tool for this is a `phase vocoder`, which involves taking a short window fft, shifting …