Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
GPU-server opened an issue on SWivid/F5-TTS
I was not impressed. I just tried it. Used the gradio and did an inference with a video game character and got halluination and bad voice result. What I am missing?
I just installed this Opened gradio, inseretd a 20 sec audio from a video game character talking (without music) Gave it a text and the result had an imaginary word at the beginning (hallucinati...
DakeQQ created a comment on an issue on SWivid/F5-TTS
Hello~ The issue with the English voice should have been resolved. Please try again using the latest F5-TTS-ONNX version. @GreenLandisaLie
SWivid created a comment on an issue on SWivid/F5-TTS
Possible solution: 1. Use less nfe_step for speed-quality trade-off. 2. Try distillation techniques. 3. Train a smaller model from scratch if single-language needed application scenario. 0....
SWivid created a comment on a pull request on SWivid/F5-TTS
Hi @v3ucn . Yes, what I mean is: will we need also change the parts in code ``` with open(file_metadata, "r", encoding="utf-8") as f: data = f.read() ``` to `utf-8-sig`, as y...
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
> > Could you provide me with your Vietnamese vocab.txt? I haven't set it up yet, and I really need it for testing. > > > [#57 (comment)](https://github.com/SWivid/F5-TTS/discussions/57#discussion...
yumoqing created a comment on an issue on SWivid/F5-TTS
# config file `` "zmq_url" : "tcp://127.0.0.1:10003", "sample_rate":16000, "vocab_file":"", "remove_silence":false, "modelname":"F5-TTS", "device":"cuda:0", "r...
justzmq created a comment on an issue on SWivid/F5-TTS
我想问下，如果我只有半个小时的语音数据，可以微调出具有该语音特色的模型么？如果可以的话，我大概需要设置怎样的微调参数？期待回复！感谢！
vu-the-dung created a comment on an issue on SWivid/F5-TTS
> Could you provide me with your Vietnamese vocab.txt? I haven't set it up yet, and I really need it for testing. > > > [#57 (comment)](https://github.com/SWivid/F5-TTS/discussions/57#discussion...
yumoqing opened an issue on SWivid/F5-TTS
can f5-tts inference more faster?
# Can f5-tts inference more faster? ## environment: Machine type:vps python:12.3 OS:ubuntu 22.04 MEM:64G vCPU:16 GPU: one of nvidia 4090 install: follow the installation step in README.md ...
SWivid created a comment on an issue on SWivid/F5-TTS
cuz attention as a quadratic mem cost, need to adjust current rough batchsampler taking longer samples into consideration, e.g. dynamically adjust threshold, smaller for longer samples.
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
Could you provide me with your Vietnamese vocab.txt? I haven't set it up yet, and I really need it for testing. > [#57 (comment)](https://github.com/SWivid/F5-TTS/discussions/57#discussioncomment-...