Update README.md
Browse filesMultiply WER and CER by 100 to reflect correct results
README.md
CHANGED
|
@@ -4,7 +4,6 @@ tags:
|
|
| 4 |
- google/fleurs
|
| 5 |
- generated_from_trainer
|
| 6 |
- automatic-speech-recognition
|
| 7 |
-
- hf-asr-leaderboard
|
| 8 |
- pashto
|
| 9 |
- ps
|
| 10 |
datasets:
|
|
@@ -24,7 +23,7 @@ model-index:
|
|
| 24 |
metrics:
|
| 25 |
- name: Wer
|
| 26 |
type: wer
|
| 27 |
-
value:
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -35,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 35 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the GOOGLE/FLEURS - PS_AF dataset.
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
- Loss: 0.9162
|
| 38 |
-
- Wer:
|
| 39 |
-
- Cer:
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
|
|
| 4 |
- google/fleurs
|
| 5 |
- generated_from_trainer
|
| 6 |
- automatic-speech-recognition
|
|
|
|
| 7 |
- pashto
|
| 8 |
- ps
|
| 9 |
datasets:
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Wer
|
| 25 |
type: wer
|
| 26 |
+
value: 51.59447476125512
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the GOOGLE/FLEURS - PS_AF dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
- Loss: 0.9162
|
| 37 |
+
- Wer: 51.59
|
| 38 |
+
- Cer: 19.72
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|