Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- sr
|
| 4 |
+
tags:
|
| 5 |
+
- audio
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
license: mit
|
| 8 |
+
library_name: ctranslate2
|
| 9 |
+
datasets:
|
| 10 |
+
- google/fleurs
|
| 11 |
+
- mozilla-foundation/common_voice_16_1
|
| 12 |
+
- Sagicc/audio-lmb-ds
|
| 13 |
+
- espnet/yodas
|
| 14 |
---
|
| 15 |
+
# Whisper Medium Yodas
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the multiple datasets.
|
| 18 |
+
|
| 19 |
+
Testing new dataset [espnet/yodas](https://huggingface.co/datasets/espnet/yodas)
|
| 20 |
+
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.1466
|
| 23 |
+
- Wer Ortho: 0.1771
|
| 24 |
+
- Wer: 0.0811
|