Commit
•
fbfdfe3
1
Parent(s):
cf7ab1e
update model card README.md
Browse files
README.md
CHANGED
|
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss:
|
| 24 |
-
- Wer: 0.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -48,17 +48,48 @@ The following hyperparameters were used during training:
|
|
| 48 |
- total_train_batch_size: 32
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
-
- lr_scheduler_warmup_steps:
|
| 52 |
-
- num_epochs:
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
-
| Training Loss | Epoch | Step
|
| 58 |
-
|
| 59 |
-
|
|
| 60 |
-
| 2.
|
| 61 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.3179
|
| 24 |
+
- Wer: 0.2735
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 48 |
- total_train_batch_size: 32
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 2000
|
| 52 |
+
- num_epochs: 50.0
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 59 |
+
| 3.3332 | 1.45 | 500 | 3.2920 | 1.0 |
|
| 60 |
+
| 2.9269 | 2.91 | 1000 | 2.9415 | 0.9966 |
|
| 61 |
+
| 2.0719 | 4.36 | 1500 | 1.1641 | 0.8508 |
|
| 62 |
+
| 1.7404 | 5.81 | 2000 | 0.7281 | 0.6846 |
|
| 63 |
+
| 1.5921 | 7.27 | 2500 | 0.5886 | 0.5147 |
|
| 64 |
+
| 1.4941 | 8.72 | 3000 | 0.5183 | 0.5063 |
|
| 65 |
+
| 1.4486 | 10.17 | 3500 | 0.4749 | 0.4676 |
|
| 66 |
+
| 1.3899 | 11.63 | 4000 | 0.4565 | 0.4432 |
|
| 67 |
+
| 1.3881 | 13.08 | 4500 | 0.4316 | 0.4228 |
|
| 68 |
+
| 1.3572 | 14.53 | 5000 | 0.4195 | 0.3834 |
|
| 69 |
+
| 1.3261 | 15.99 | 5500 | 0.3974 | 0.3607 |
|
| 70 |
+
| 1.2809 | 17.44 | 6000 | 0.3845 | 0.3467 |
|
| 71 |
+
| 1.2713 | 18.89 | 6500 | 0.3832 | 0.3450 |
|
| 72 |
+
| 1.257 | 20.35 | 7000 | 0.3779 | 0.3373 |
|
| 73 |
+
| 1.2298 | 21.8 | 7500 | 0.3744 | 0.3391 |
|
| 74 |
+
| 1.2173 | 23.26 | 8000 | 0.3745 | 0.3262 |
|
| 75 |
+
| 1.1966 | 24.71 | 8500 | 0.3680 | 0.3241 |
|
| 76 |
+
| 1.1925 | 26.16 | 9000 | 0.3605 | 0.3171 |
|
| 77 |
+
| 1.1692 | 27.61 | 9500 | 0.3512 | 0.3147 |
|
| 78 |
+
| 1.1704 | 29.07 | 10000 | 0.3532 | 0.3098 |
|
| 79 |
+
| 1.1595 | 30.52 | 10500 | 0.3425 | 0.3039 |
|
| 80 |
+
| 1.1433 | 31.97 | 11000 | 0.3568 | 0.3026 |
|
| 81 |
+
| 1.1295 | 33.43 | 11500 | 0.3461 | 0.2992 |
|
| 82 |
+
| 1.1131 | 34.88 | 12000 | 0.3349 | 0.2942 |
|
| 83 |
+
| 1.1015 | 36.34 | 12500 | 0.3378 | 0.2961 |
|
| 84 |
+
| 1.0835 | 37.79 | 13000 | 0.3282 | 0.2865 |
|
| 85 |
+
| 1.083 | 39.24 | 13500 | 0.3182 | 0.2826 |
|
| 86 |
+
| 1.0819 | 40.7 | 14000 | 0.3264 | 0.2850 |
|
| 87 |
+
| 1.072 | 42.15 | 14500 | 0.3279 | 0.2817 |
|
| 88 |
+
| 1.0456 | 43.6 | 15000 | 0.3234 | 0.2793 |
|
| 89 |
+
| 1.0581 | 45.06 | 15500 | 0.3220 | 0.2779 |
|
| 90 |
+
| 1.0406 | 46.51 | 16000 | 0.3208 | 0.2762 |
|
| 91 |
+
| 1.0422 | 47.96 | 16500 | 0.3184 | 0.2752 |
|
| 92 |
+
| 1.0099 | 49.42 | 17000 | 0.3181 | 0.2735 |
|
| 93 |
|
| 94 |
|
| 95 |
### Framework versions
|