fish-speech
fish-speech copied to clipboard
SOTA Open Source TTS
Feel free to ask any kind of questions in the issues page, but please use English since other users may find your questions valuable. **Is your feature request related to...
**Is this PR adding new feature or fix a BUG?** Add feature / Fix BUG. **Is this pull request related to any issue? If yes, please link the issue.** #xxx
在文本生成语义token阶段,想加速,加了--compile参数,但是出现错误,去掉--compile参数就不会出错 指令如下’python tools/llama/generate.py --text "位于中国广东省深圳市南山区粤海路1006号" --prompt-text "The text corresponding to reference audio" --prompt-tokens "fake.npy" --checkpoint-path "H:\workProject\WorkProject\HangDian\dataSet\x\tts\fish-speech-1.2\checkpoints" --num-samples 2 --compile ‘,产生错误,  环境是:pytorch 2.3.1+cu121,gpu:rtx4060ti
We are comparing models and we currently only have 24 kHz datasets. Would you know which configurations I would need for training the VQ and text models for this sampling...
Feel free to ask any kind of questions in the issues page, but please use English since other users may find your questions valuable. **Describe the bug** A clear and...
Feel free to ask any kind of questions in the issues page, but please use English since other users may find your questions valuable. **Describe the bug** Use webui and...
Feel free to ask any kind of questions in the issues page, but please use English since other users may find your questions valuable. **Describe the bug** A clear and...