Sync from GitHub repo
Browse filesThis Space is synced from the GitHub repo: https://github.com/SWivid/F5-TTS. Please submit contributions to the Space there
- src/f5_tts/infer/SHARED.md +12 -5
src/f5_tts/infer/SHARED.md
CHANGED
|
@@ -20,6 +20,7 @@
|
|
| 20 |
- [Mandarin](#mandarin)
|
| 21 |
- [English](#english)
|
| 22 |
- [French](#french)
|
|
|
|
| 23 |
|
| 24 |
|
| 25 |
## Multilingual
|
|
@@ -33,14 +34,19 @@
|
|
| 33 |
MODEL_CKPT: hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors
|
| 34 |
VOCAB_FILE: hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt
|
| 35 |
```
|
|
|
|
| 36 |
*Other infos, e.g. Author info, Github repo, Link to some sampled results, Usage instruction, Tutorial (Blog, Video, etc.) ...*
|
| 37 |
|
|
|
|
| 38 |
## Mandarin
|
| 39 |
|
| 40 |
|
| 41 |
## English
|
| 42 |
|
|
|
|
| 43 |
## French
|
|
|
|
|
|
|
| 44 |
|Model|π€Hugging Face|Data (Hours)|Model License|
|
| 45 |
|:---:|:------------:|:-----------:|:-------------:|
|
| 46 |
|F5-TTS French|[ckpt & vocab](https://huggingface.co/RASPIAUDIO/F5-French-MixedSpeakers-reduced)|[LibriVox](https://librivox.org/)|cc-by-nc-4.0|
|
|
@@ -49,11 +55,12 @@ VOCAB_FILE: hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt
|
|
| 49 |
MODEL_CKPT: hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/model_last_reduced.pt
|
| 50 |
VOCAB_FILE: hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/vocab.txt
|
| 51 |
```
|
| 52 |
-
### Online Inference
|
| 53 |
-
You can test the model online using our [Hugging Face Space](https://huggingface.co/spaces/RASPIAUDIO/f5-tts_french).
|
| 54 |
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
|
|
|
|
| 20 |
- [Mandarin](#mandarin)
|
| 21 |
- [English](#english)
|
| 22 |
- [French](#french)
|
| 23 |
+
- [French LibriVox @ finetune @ fr](#french-librivox--finetune--fr)
|
| 24 |
|
| 25 |
|
| 26 |
## Multilingual
|
|
|
|
| 34 |
MODEL_CKPT: hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors
|
| 35 |
VOCAB_FILE: hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt
|
| 36 |
```
|
| 37 |
+
|
| 38 |
*Other infos, e.g. Author info, Github repo, Link to some sampled results, Usage instruction, Tutorial (Blog, Video, etc.) ...*
|
| 39 |
|
| 40 |
+
|
| 41 |
## Mandarin
|
| 42 |
|
| 43 |
|
| 44 |
## English
|
| 45 |
|
| 46 |
+
|
| 47 |
## French
|
| 48 |
+
|
| 49 |
+
#### French LibriVox @ finetune @ fr
|
| 50 |
|Model|π€Hugging Face|Data (Hours)|Model License|
|
| 51 |
|:---:|:------------:|:-----------:|:-------------:|
|
| 52 |
|F5-TTS French|[ckpt & vocab](https://huggingface.co/RASPIAUDIO/F5-French-MixedSpeakers-reduced)|[LibriVox](https://librivox.org/)|cc-by-nc-4.0|
|
|
|
|
| 55 |
MODEL_CKPT: hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/model_last_reduced.pt
|
| 56 |
VOCAB_FILE: hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/vocab.txt
|
| 57 |
```
|
|
|
|
|
|
|
| 58 |
|
| 59 |
+
**Online Inference**
|
| 60 |
+
You can test the model online with [Hugging Face Space](https://huggingface.co/spaces/RASPIAUDIO/f5-tts_french).
|
| 61 |
+
|
| 62 |
+
**Resources**
|
| 63 |
+
1.[Tutorial video to train a new language model](https://www.youtube.com/watch?v=UO4usaOojys).
|
| 64 |
+
2.[Discussion about this training can be found here](https://github.com/SWivid/F5-TTS/issues/434).
|
| 65 |
|
| 66 |
|