Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,28 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-sa-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Wikidepia/openslr_enhanced
|
| 5 |
+
language:
|
| 6 |
+
- id
|
| 7 |
+
- jv
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Montreal Forced Aligner (MFA) for Indonesian-Javanese (Indo+)
|
| 11 |
+
|
| 12 |
+
This repository contains MFA model for Indonesian-Javanese language. This model primarily trained on Javanese ASR dataset (https://www.openslr.org/35/), that are enhanced using DeepFilterNet2 to remove unwanted noise. Lexicon contained in this repository comes from Google's language-resource [Javanese Lexicon](https://github.com/google/language-resources/blob/master/jv/data/lexicon.tsv).
|
| 13 |
+
|
| 14 |
+
## Example Usage
|
| 15 |
+
|
| 16 |
+
To align:
|
| 17 |
+
|
| 18 |
+
```bash
|
| 19 |
+
mfa align --g2p_model_path g2p_jv.zip audio_dir lexicon_jv.dict acoustic_model.zip aligned_dir
|
| 20 |
+
```
|
| 21 |
+
|
| 22 |
+
## Resources
|
| 23 |
+
- https://montreal-forced-aligner.readthedocs.io/en/latest/first_steps/alignment_example.html
|
| 24 |
+
- https://mfa-models.readthedocs.io/en/latest/
|
| 25 |
+
|
| 26 |
+
## License
|
| 27 |
+
|
| 28 |
+
CC-BY-SA-4.0
|