Update README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,12 @@ As a base model, we used a previously fine-tuned ASR model for [Latvian](https:/
|
|
23 |
|
24 |
## Evaluation
|
25 |
|
26 |
-
|
|
|
|
|
|
|
|
|
|
|
27 |
|
28 |
## Acknowledgements
|
29 |
|
|
|
23 |
|
24 |
## Evaluation
|
25 |
|
26 |
+
| Testing data | WER |
|
27 |
+
|:---|---:|
|
28 |
+
| Latgalian CV 20.0 test set (1.5 hours) | 9.1 |
|
29 |
+
| MuLaR test set (1.6 hours) | 25.7 |
|
30 |
+
|
31 |
+
NB! The MuLaR corpus contains transcriptions that generally do not follow the rules of the standard Latgalian orthography, in contrast to the Latgalian CV corpus.
|
32 |
|
33 |
## Acknowledgements
|
34 |
|