mrfakename commited on
Commit
7fc7ada
1 Parent(s): 56c4c0e

Sync from GitHub repo

Browse files

This Space is synced from the GitHub repo: https://github.com/SWivid/F5-TTS. Please submit contributions to the Space there

Files changed (1) hide show
  1. src/f5_tts/infer/SHARED.md +36 -20
src/f5_tts/infer/SHARED.md CHANGED
@@ -17,14 +17,17 @@
17
  ### Supported Languages
18
  - [Multilingual](#multilingual)
19
  - [F5-TTS Base @ pretrain @ zh \& en](#f5-tts-base--pretrain--zh--en)
20
- - [Mandarin](#mandarin)
21
- - [Japanese](#japanese)
22
- - [F5-TTS Base @ pretrain/finetune @ ja](#f5-tts-base--pretrainfinetune--ja)
23
  - [English](#english)
 
 
24
  - [French](#french)
25
  - [French LibriVox @ finetune @ fr](#french-librivox--finetune--fr)
26
- - [Finnish](#finnish)
27
- - [Finnish Common Voice Vox Populi @ finetune @ fi](#finnish-common-voice-vox-populi--finetune--fi)
 
 
 
 
28
 
29
  ## Multilingual
30
 
@@ -40,21 +43,22 @@ VOCAB_FILE: hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt
40
 
41
  *Other infos, e.g. Author info, Github repo, Link to some sampled results, Usage instruction, Tutorial (Blog, Video, etc.) ...*
42
 
43
- ## Mandarin
44
 
45
- ## Japanese
46
 
47
- #### F5-TTS Base @ pretrain/finetune @ ja
48
- |Model|🤗Hugging Face|Data (Hours)|Model License|
 
 
 
49
  |:---:|:------------:|:-----------:|:-------------:|
50
- |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|
51
 
52
  ```bash
53
- MODEL_CKPT: hf://Jmica/F5TTS/JA_8500000/model_8499660.pt
54
- VOCAB_FILE: hf://Jmica/F5TTS/JA_8500000/vocab_updated.txt
55
  ```
56
 
57
- ## English
58
 
59
  ## French
60
 
@@ -72,16 +76,28 @@ VOCAB_FILE: hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/vocab.txt
72
  - [Tutorial video to train a new language model](https://www.youtube.com/watch?v=UO4usaOojys).
73
  - [Discussion about this training can be found here](https://github.com/SWivid/F5-TTS/issues/434).
74
 
75
- ## English
76
 
77
- ## Finnish
78
 
79
- #### Finnish Common_Voice Vox_Populi @ finetune @ fi
80
- |Model|🤗Hugging Face|Data|Model License|
81
  |:---:|:------------:|:-----------:|:-------------:|
82
- |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|
83
 
84
  ```bash
85
- MODEL_CKPT: hf://AsmoKoskinen/F5-TTS_Finish_Model/model_common_voice_fi_vox_populi_fi_20241206.safetensors
86
- VOCAB_FILE: hf://AsmoKoskinen/F5-TTS_Finish_Model/vocab.txt
87
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  ### Supported Languages
18
  - [Multilingual](#multilingual)
19
  - [F5-TTS Base @ pretrain @ zh \& en](#f5-tts-base--pretrain--zh--en)
 
 
 
20
  - [English](#english)
21
+ - [Finnish](#finnish)
22
+ - [Finnish Common\_Voice Vox\_Populi @ finetune @ fi](#finnish-common_voice-vox_populi--finetune--fi)
23
  - [French](#french)
24
  - [French LibriVox @ finetune @ fr](#french-librivox--finetune--fr)
25
+ - [Japanese](#japanese)
26
+ - [F5-TTS Japanese @ pretrain/finetune @ ja](#f5-tts-japanese--pretrainfinetune--ja)
27
+ - [Mandarin](#mandarin)
28
+ - [Spanish](#spanish)
29
+ - [F5-TTS Spanish @ pretrain/finetune @ es](#f5-tts-spanish--pretrainfinetune--es)
30
+
31
 
32
  ## Multilingual
33
 
 
43
 
44
  *Other infos, e.g. Author info, Github repo, Link to some sampled results, Usage instruction, Tutorial (Blog, Video, etc.) ...*
45
 
 
46
 
47
+ ## English
48
 
49
+
50
+ ## Finnish
51
+
52
+ #### Finnish Common_Voice Vox_Populi @ finetune @ fi
53
+ |Model|🤗Hugging Face|Data|Model License|
54
  |:---:|:------------:|:-----------:|:-------------:|
55
+ |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|
56
 
57
  ```bash
58
+ MODEL_CKPT: hf://AsmoKoskinen/F5-TTS_Finish_Model/model_common_voice_fi_vox_populi_fi_20241206.safetensors
59
+ VOCAB_FILE: hf://AsmoKoskinen/F5-TTS_Finish_Model/vocab.txt
60
  ```
61
 
 
62
 
63
  ## French
64
 
 
76
  - [Tutorial video to train a new language model](https://www.youtube.com/watch?v=UO4usaOojys).
77
  - [Discussion about this training can be found here](https://github.com/SWivid/F5-TTS/issues/434).
78
 
 
79
 
80
+ ## Japanese
81
 
82
+ #### F5-TTS Japanese @ pretrain/finetune @ ja
83
+ |Model|🤗Hugging Face|Data (Hours)|Model License|
84
  |:---:|:------------:|:-----------:|:-------------:|
85
+ |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|
86
 
87
  ```bash
88
+ MODEL_CKPT: hf://Jmica/F5TTS/JA_8500000/model_8499660.pt
89
+ VOCAB_FILE: hf://Jmica/F5TTS/JA_8500000/vocab_updated.txt
90
  ```
91
+
92
+
93
+ ## Mandarin
94
+
95
+
96
+ ## Spanish
97
+
98
+ #### F5-TTS Spanish @ pretrain/finetune @ es
99
+ |Model|🤗Hugging Face|Data (Hours)|Model License|
100
+ |:---:|:------------:|:-----------:|:-------------:|
101
+ |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|
102
+
103
+ - @jpgallegoar [GitHub repo](https://github.com/jpgallegoar/Spanish-F5), Jupyter Notebook and Gradio usage for Spanish model.