Commit
·
fc2e79f
1
Parent(s):
14eb05a
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: ASR-Somali
|
| 7 |
results: []
|
|
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
# ASR-Somali
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -43,6 +48,23 @@ The following hyperparameters were used during training:
|
|
| 43 |
- num_epochs: 30
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.28.0
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
model-index:
|
| 8 |
- name: ASR-Somali
|
| 9 |
results: []
|
|
|
|
| 15 |
# ASR-Somali
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3660
|
| 20 |
+
- Wer: 0.3060
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 48 |
- num_epochs: 30
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 3.1435 | 2.09 | 400 | 0.7624 | 0.7706 |
|
| 56 |
+
| 0.5829 | 4.18 | 800 | 0.3646 | 0.3935 |
|
| 57 |
+
| 0.3634 | 6.27 | 1200 | 0.3318 | 0.3944 |
|
| 58 |
+
| 0.2942 | 8.36 | 1600 | 0.3148 | 0.3403 |
|
| 59 |
+
| 0.2419 | 10.44 | 2000 | 0.3000 | 0.3255 |
|
| 60 |
+
| 0.2104 | 12.53 | 2400 | 0.2951 | 0.3312 |
|
| 61 |
+
| 0.1864 | 14.62 | 2800 | 0.3296 | 0.3083 |
|
| 62 |
+
| 0.1666 | 16.71 | 3200 | 0.3264 | 0.3153 |
|
| 63 |
+
| 0.148 | 18.8 | 3600 | 0.3188 | 0.3028 |
|
| 64 |
+
| 0.1305 | 20.89 | 4000 | 0.3448 | 0.3002 |
|
| 65 |
+
| 0.1206 | 22.98 | 4400 | 0.3660 | 0.3060 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- Transformers 4.28.0
|