Update README.md
Browse files
README.md
CHANGED
|
@@ -36,4 +36,10 @@ datasets:
|
|
| 36 |
|
| 37 |
#### Click the tab *training metrics* above to view the live Tensorboard of the model training with the small (2880 samples), with the expanded (27072 samples) dataset, each with and without data augmentation.
|
| 38 |
|
| 39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
|
| 37 |
#### Click the tab *training metrics* above to view the live Tensorboard of the model training with the small (2880 samples), with the expanded (27072 samples) dataset, each with and without data augmentation.
|
| 38 |
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
#### The speech recognition models for the other languages have been released by Coqui.ai in the [model zoo](https://coqui.ai/models). I use the following versions in my ASR system:
|
| 42 |
+
* [French STT v0.9](https://coqui.ai/french/commonvoice-fr/v0.9) Dataset : common-voice.fr
|
| 43 |
+
* [German STT v0.9](https://coqui.ai/german/AASHISHAG/v0.9.0) Datasets : Common Voice 5.1, SWC , MAILABS, Tuda-De, Voxforge
|
| 44 |
+
* [English STT huge vocab v1.0](https://coqui.ai/english/coqui/v1.0.0-huge-vocab) Datasets : Common Voice 7.0, Librispeech
|
| 45 |
+
* [Portuguese STT v0.1.1](https://coqui.ai/portuguese/itml/v0.1.1) Dataset : Common Voice 6.1
|