Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
vu-the-dung created a comment on an issue on SWivid/F5-TTS
@PhamDangNguyen my dataset already have normalized text, even without punctuation. And after some test inferences with punctuation in gen_text, I'm feeling like the model have forgotten to pause at...
SWivid created a comment on an issue on SWivid/F5-TTS
@jpgallegoar initial prune done. That convenient button to add `{stype}` not yet
vu-the-dung created a comment on an issue on SWivid/F5-TTS
I only tested with Vietnamese. I saw that after adding missing Vietnamese characters to vocab.txt, when calling convert_char_to_pinyin with a sentence in Vietnamese, the returned char array often h...
liuhui881125 created a comment on an issue on SWivid/F5-TTS
After rolling back this commit, it can run, but the generated file is a current sound. [46d391a](url) [](https://github.com/SWivid/F5-TTS/commit/46d391a8766d8eabb967b326ccb473bc2d8b9a6c)
PhamDangNguyen opened an issue on SWivid/F5-TTS
When I fine-tune model, Do i need to modify "convert_char_to_pinyin" by other function ?
Chinese is a unique language. When I want to train and process with other languages, such as Vietnamese, Spanish, or Lao, do I need to change the data processing method? Specifically, the function ...
CamellIyquitous created a comment on an issue on SWivid/F5-TTS
> I had a similar issue and resolved it by installing a different version of the package. > > Replace this: > > ``` > pip install torch==2.3.0+cu118 torchaudio==2.3.0+cu118 --extra-index-url...
yachuntsaikk created a comment on an issue on SWivid/F5-TTS
I had a similar issue and resolved it by installing a different version of the package. Replace this: ``` pip install torch==2.3.0+cu118 torchaudio==2.3.0+cu118 --extra-index-url https://dow...
SWivid created a comment on an issue on SWivid/F5-TTS
> Ah! It is needed to have a app.py outside? Will take care of that. try with just `infer_gradio.py` inside, will work if done `pip install -e .`
PhamDangNguyen closed an issue on SWivid/F5-TTS
How can I tokenize text into the desired size using the code in this repository?
**I get an error when i run inference-cli.py with my code:** python inference-cli.py \ --model "F5-TTS" \ --ref_audio "/home/pdnguyen/TTS/F5-TTS/notebooks/data/fine-tune/wavs/chunk_2.wav" \ --r...
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
I got it. The problem may be solved. Thanks
vu-the-dung created a comment on an issue on SWivid/F5-TTS
@PhamDangNguyen if you run inference-cli.py without providing your own checkpoint path in --ckpt_file, it will load F5/E2 TTS pretrained checkpoint as default https://github.com/SWivid/F5-TTS/blob...
SWivid pushed 1 commit to main SWivid/F5-TTS
- fix path finetune gradio (#262) * fix path * change name 33d903b
SWivid closed a pull request on SWivid/F5-TTS
fix path finetune gradio
@SWivid hi i fix path to work with last update
jpgallegoar created a comment on an issue on SWivid/F5-TTS
> @jpgallegoar Hi, it's basically for sync_f5 used previous setup way We move to `pyproject.toml` and not with `requirement.txt` now > > @fakerybakery might help with the tweak things > > Ah!...
SWivid created a comment on an issue on SWivid/F5-TTS
@PhamDangNguyen We have the link https://github.com/SWivid/F5-TTS?tab=readme-ov-file#news And we have mentioned the ckpt_file path in >@PhamDangNguyen have you got through training readme yet?...
PhamDangNguyen reopened an issue on SWivid/F5-TTS
How can I tokenize text into the desired size using the code in this repository?
**I get an error when i run inference-cli.py with my code:** python inference-cli.py \ --model "F5-TTS" \ --ref_audio "/home/pdnguyen/TTS/F5-TTS/notebooks/data/fine-tune/wavs/chunk_2.wav" \ --r...
PhamDangNguyen closed an issue on SWivid/F5-TTS
How can I tokenize text into the desired size using the code in this repository?
**I get an error when i run inference-cli.py with my code:** python inference-cli.py \ --model "F5-TTS" \ --ref_audio "/home/pdnguyen/TTS/F5-TTS/notebooks/data/fine-tune/wavs/chunk_2.wav" \ --r...