gitea-mirror/F5-TTS
1
0
Fork 0
mirror of https://github.com/SWivid/F5-TTS.git synced 2026-01-02 16:20:27 -08:00
Code Issues Packages Projects Releases Wiki Activity

formatting. fi & es in shared.md

Browse Source
This commit is contained in:
SWivid
2024-12-07 14:04:15 +08:00
parent 714fade533
commit 9acfea0fd2
1 changed files with 41 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
src/f5_tts/infer/SHARED.md
View File

@@ -17,14 +17,17 @@
### Supported Languages
- [Multilingual](#multilingual)
- [F5-TTS Base @ pretrain @ zh \& en](#f5-tts-base--pretrain--zh--en)
- [Mandarin](#mandarin)
- [Japanese](#japanese)
- [F5-TTS Base @ pretrain/finetune @ ja](#f5-tts-base--pretrainfinetune--ja)
- [English](#english)
- [Finnish](#finnish)
- [Finnish Common\_Voice Vox\_Populi @ finetune @ fi](#finnish-common_voice-vox_populi--finetune--fi)
- [French](#french)
- [French LibriVox @ finetune @ fr](#french-librivox--finetune--fr)
- [Finnish](#finnish)
- [Finnish Common Voice Vox Populi @ finetune @ fi](#finnish-common-voice-vox-populi--finetune--fi)
- [Japanese](#japanese)
- [F5-TTS Japanese @ pretrain/finetune @ ja](#f5-tts-japanese--pretrainfinetune--ja)
- [Mandarin](#mandarin)
- [Spanish](#spanish)
- [F5-TTS Spanish @ pretrain/finetune @ es](#f5-tts-spanish--pretrainfinetune--es)
## Multilingual
@@ -40,22 +43,23 @@ VOCAB_FILE: hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt
*Other infos, e.g. Author info, Github repo, Link to some sampled results, Usage instruction, Tutorial (Blog, Video, etc.) ...*
## Mandarin
## Japanese
#### F5-TTS Base @ pretrain/finetune @ ja
|Model|🤗Hugging Face|Data (Hours)|Model License|
|:---:|:------------:|:-----------:|:-------------:|
|F5-TTS Base|[ckpt & vocab](https://huggingface.co/Jmica/F5TTS/tree/main/JA_8500000)|[Emilia 1.7k JA](https://huggingface.co/datasets/amphion/Emilia-Dataset/tree/fc71e07) & [Galgame Dataset 5.4k](https://huggingface.co/datasets/OOPPEENN/Galgame_Dataset)|cc-by-nc-4.0|
```bash
MODEL_CKPT: hf://Jmica/F5TTS/JA_8500000/model_8499660.pt
VOCAB_FILE: hf://Jmica/F5TTS/JA_8500000/vocab_updated.txt
```
## English
## Finnish
#### Finnish Common_Voice Vox_Populi @ finetune @ fi
|Model|🤗Hugging Face|Data|Model License|
|:---:|:------------:|:-----------:|:-------------:|
|F5-TTS Finnish|[ckpt & vocab](https://huggingface.co/AsmoKoskinen/F5-TTS_Finnish_Model)|[Common Voice](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0), [Vox Populi](https://huggingface.co/datasets/facebook/voxpopuli)|cc-by-nc-4.0|
```bash
MODEL_CKPT: hf://AsmoKoskinen/F5-TTS_Finish_Model/model_common_voice_fi_vox_populi_fi_20241206.safetensors
VOCAB_FILE: hf://AsmoKoskinen/F5-TTS_Finish_Model/vocab.txt
```
## French
#### French LibriVox @ finetune @ fr
@@ -72,16 +76,28 @@ VOCAB_FILE: hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/vocab.txt
- [Tutorial video to train a new language model](https://www.youtube.com/watch?v=UO4usaOojys).
- [Discussion about this training can be found here](https://github.com/SWivid/F5-TTS/issues/434).
## English
## Finnish
## Japanese
#### Finnish Common_Voice Vox_Populi @ finetune @ fi
|Model|🤗Hugging Face|Data|Model License|
#### F5-TTS Japanese @ pretrain/finetune @ ja
|Model|🤗Hugging Face|Data (Hours)|Model License|
|:---:|:------------:|:-----------:|:-------------:|
|F5-TTS Finnish|[ckpt & vocab](https://huggingface.co/AsmoKoskinen/F5-TTS_Finnish_Model)|[Common Voice](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0), [Vox Populi](https://huggingface.co/datasets/facebook/voxpopuli)|cc-by-nc-4.0|
|F5-TTS Japanese|[ckpt & vocab](https://huggingface.co/Jmica/F5TTS/tree/main/JA_8500000)|[Emilia 1.7k JA](https://huggingface.co/datasets/amphion/Emilia-Dataset/tree/fc71e07) & [Galgame Dataset 5.4k](https://huggingface.co/datasets/OOPPEENN/Galgame_Dataset)|cc-by-nc-4.0|
```bash
MODEL_CKPT: hf://AsmoKoskinen/F5-TTS_Finish_Model/model_common_voice_fi_vox_populi_fi_20241206.safetensors
VOCAB_FILE: hf://AsmoKoskinen/F5-TTS_Finish_Model/vocab.txt
MODEL_CKPT: hf://Jmica/F5TTS/JA_8500000/model_8499660.pt
VOCAB_FILE: hf://Jmica/F5TTS/JA_8500000/vocab_updated.txt
```
## Mandarin
## Spanish
#### F5-TTS Spanish @ pretrain/finetune @ es
|Model|🤗Hugging Face|Data (Hours)|Model License|
|:---:|:------------:|:-----------:|:-------------:|
|F5-TTS Spanish|[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.