gitea-mirror/F5-TTS
1
0
Fork 0
mirror of https://github.com/SWivid/F5-TTS.git synced 2025-12-05 20:40:12 -08:00
Code Issues Packages Projects Releases Wiki Activity

formatting

Browse Source
This commit is contained in:
SWivid
2025-06-03 21:23:47 +08:00
parent 1d13664b24
commit 31cd818095
2 changed files with 14 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
src/f5_tts/infer/SHARED.md
View File

@@ -22,6 +22,8 @@
- [F5-TTS Base @ fi @ AsmoKoskinen](#f5-tts-base--fi--asmokoskinen)
- [French](#french)
- [F5-TTS Base @ fr @ RASPIAUDIO](#f5-tts-base--fr--raspiaudio)
- [German](#german)
- [F5-TTS Base @ de @ hvoss-techfak](#f5-tts-base--de--hvoss-techfak)
- [Hindi](#hindi)
- [F5-TTS Small @ hi @ SPRINGLab](#f5-tts-small--hi--springlab)
- [Italian](#italian)
@@ -33,8 +35,6 @@
- [F5-TTS Base @ ru @ HotDro4illa](#f5-tts-base--ru--hotdro4illa)
- [Spanish](#spanish)
- [F5-TTS Base @ es @ jpgallegoar](#f5-tts-base--es--jpgallegoar)
- [German](#german)
- [F5-TTS Base @ de @ hvoss-techfak](#f5-tts-base--de--hvoss-techfak)
## Multilingual
@@ -99,6 +99,16 @@ Config: {"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "
- [Discussion about this training can be found here](https://github.com/SWivid/F5-TTS/issues/434).
## German
#### F5-TTS Base @ de @ hvoss-techfak
|Model|🤗Hugging Face|Data (Hours)|Model License|
|:---:|:------------:|:-----------:|:-------------:|
|F5-TTS Base|[ckpt & vocab](https://huggingface.co/hvoss-techfak/F5-TTS-German)|[Mozilla Common Voice 19.0](https://commonvoice.mozilla.org/en/datasets) & 800 hours Crowdsourced |cc-by-nc-4.0|
- Finetuned by [@hvoss-techfak](https://github.com/hvoss-techfak)
## Hindi
#### F5-TTS Small @ hi @ SPRINGLab
@@ -175,12 +185,3 @@ Config: {"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "
|F5-TTS Base|[ckpt & vocab](https://huggingface.co/jpgallegoar/F5-Spanish)|[Voxpopuli](https://huggingface.co/datasets/facebook/voxpopuli) & Crowdsourced & TEDx, 218 hours|cc0-1.0|
- @jpgallegoar [GitHub repo](https://github.com/jpgallegoar/Spanish-F5), Jupyter Notebook and Gradio usage for Spanish model.
## German
#### F5-TTS Base @ de @ hvoss-techfak
|Model|🤗Hugging Face|Data (Hours)|Model License|
|:---:|:------------:|:-----------:|:-------------:|
|F5-TTS Base|[ckpt & vocab](https://huggingface.co/hvoss-techfak/F5-TTS-German)|[Mozilla Common Voice 19.0](https://commonvoice.mozilla.org/en/datasets) & 800 hours Crowdsourced |cc-by-nc-4.0|
- Finetuned by [@hvoss-techfak](https://github.com/hvoss-techfak)

4
src/f5_tts/train/finetune_gradio.py
View File

@@ -434,7 +434,7 @@ def start_training(
fp16 = ""
cmd = (
f"accelerate launch {fp16} \"{file_train}\" --exp_name {exp_name}"
f'accelerate launch {fp16} "{file_train}" --exp_name {exp_name}'
f" --learning_rate {learning_rate}"
f" --batch_size_per_gpu {batch_size_per_gpu}"
f" --batch_size_type {batch_size_type}"
@@ -453,7 +453,7 @@ def start_training(
cmd += " --finetune"
if file_checkpoint_train != "":
cmd += f" --pretrain \"{file_checkpoint_train}\""
cmd += f' --pretrain "{file_checkpoint_train}"'
if tokenizer_file != "":
cmd += f" --tokenizer_path {tokenizer_file}"