Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,8 @@ tags:
|
|
| 12 |
- tts
|
| 13 |
- f5-tts
|
| 14 |
- brasil
|
| 15 |
-
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# F5-TTS-pt-br:
|
|
@@ -20,9 +21,11 @@ tags:
|
|
| 20 |
Contains pre-trained weights for Portuguese BR in F5-TTS. It only speaks portuguese as it is a preliminary test.
|
| 21 |
Tokenizer is the same as original F5-TTS from https://huggingface.co/SWivid/F5-TTS.
|
| 22 |
|
| 23 |
-
Trained on +-130hrs
|
| 24 |
128k samples with mostly 5s for 2 days on colab A100 + 2 days with T4,
|
| 25 |
and upgraded to new dataset +-200hrs 30k samples in 2 days with mostly 20s on A100
|
|
|
|
|
|
|
| 26 |
|
| 27 |
Use lower case, and for numbers use num2words. Sample bellow.
|
| 28 |
|
|
|
|
| 12 |
- tts
|
| 13 |
- f5-tts
|
| 14 |
- brasil
|
| 15 |
+
datasets:
|
| 16 |
+
- firstpixel/pt-br_char
|
| 17 |
---
|
| 18 |
|
| 19 |
# F5-TTS-pt-br:
|
|
|
|
| 21 |
Contains pre-trained weights for Portuguese BR in F5-TTS. It only speaks portuguese as it is a preliminary test.
|
| 22 |
Tokenizer is the same as original F5-TTS from https://huggingface.co/SWivid/F5-TTS.
|
| 23 |
|
| 24 |
+
Trained on +-130hrs
|
| 25 |
128k samples with mostly 5s for 2 days on colab A100 + 2 days with T4,
|
| 26 |
and upgraded to new dataset +-200hrs 30k samples in 2 days with mostly 20s on A100
|
| 27 |
+
Added 3 days on 3500 speakers from, 60k samples audios joined with from 20 to 25s of
|
| 28 |
+
https://commonvoice.mozilla.org/pt
|
| 29 |
|
| 30 |
Use lower case, and for numbers use num2words. Sample bellow.
|
| 31 |
|