Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
lpscr opened a pull request on SWivid/F5-TTS
fix path finetune gradio
@SWivid hi i fix path to work with last update
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
@SWivid This means have not pre-train check-point to load here. I still train from scratch, but architechture is F5-TTS bruh?
liuhui881125 opened an issue on SWivid/F5-TTS
RuntimeError: Error(s) in loading state_dict for CFM
Download Vocos from huggingface charactr/vocos-mel-24khz vocab : /root/F5-TTS/src/f5_tts/infer/examples/vocab.txt tokenizer : custom model : /root/F5-TTS/ckpts/F5TTS_Base/model_1200000.safete...
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
@SWivid This mean have not pre-train check-point to load here. I still train from scratch, but architecture is F5-TTS bruh
SWivid created a comment on an issue on SWivid/F5-TTS
Ah we refer to F5/E2 TTS as pretrained model lol
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
@SWivid I know you're using a pre-trained model, but currently, after reviewing the code, I haven’t found where the code loads the pre-trained model. Could you please show me? Thank you!
SWivid 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
SWivid created a comment on an issue on SWivid/F5-TTS
@PhamDangNguyen have you got through training readme yet? https://github.com/SWivid/F5-TTS/tree/main/src/f5_tts/train
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
@SWivid Is this checkpoint_path in the Trainer class? ``` self.epochs = epochs self.num_warmup_updates = num_warmup_updates self.save_per_updates = save_per_updates se...
SWivid created a comment on an issue on SWivid/F5-TTS
@LSliu666 Sure, hope this temporary strategy would help. We don't mean to limit model's ability on that, rather the model is limit with dataset (if you could just provide a bunch of perfect data, ...
SWivid closed an issue on SWivid/F5-TTS
How to optimize the mispronunciation of Chinese polyphonic characters
How to optimize the mispronunciation of Chinese polyphonic characters
jpgallegoar opened an issue on SWivid/F5-TTS
Is the new packaged version compatible with Huggingface Spaces and Pinokio?
Thanks for your efforts @SWivid in transforming the app. However the new version has broken the apps available on huggingface and pinokio. Do you know if its possible to use packaged apps there?
LSliu666 created a comment on an issue on SWivid/F5-TTS
> 追求发音准确而不是单词准确，哈哈，音符 The meaning of this is that I have found an alternative method for mispronouncing polyphonic characters, which is to replace the Chinese character of a polyphonic character...
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
> @PhamDangNguyen Sure, or you could just use the code, and train from scratch please show me path to load pre-train model in your repo!! I don't find it :v
SWivid created a comment on an issue on SWivid/F5-TTS
> @LSliu666 Mainly for dataset. A good dataset covering most cases and transcribed just correctly will let model do better on this. @LSliu666 Or you could just provide us with some data, we will...
LSliu666 created a comment on an issue on SWivid/F5-TTS
Pursuing accurate pronunciation rather than word accuracy, haha, interesting
