update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Wer: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -45,26 +45,45 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 500
|
| 48 |
-
- num_epochs:
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch | Step
|
| 54 |
-
|
| 55 |
-
| 3.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
-
- Transformers 4.23.
|
| 68 |
-
- Pytorch 1.12.1+
|
| 69 |
- Datasets 2.5.2
|
| 70 |
- Tokenizers 0.13.1
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4316
|
| 20 |
+
- Wer: 0.2905
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- num_epochs: 100
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 3.9953 | 3.67 | 400 | 0.7024 | 0.7226 |
|
| 56 |
+
| 0.4046 | 7.34 | 800 | 0.4342 | 0.5343 |
|
| 57 |
+
| 0.201 | 11.01 | 1200 | 0.4396 | 0.5290 |
|
| 58 |
+
| 0.1513 | 14.68 | 1600 | 0.4319 | 0.4108 |
|
| 59 |
+
| 0.1285 | 18.35 | 2000 | 0.4422 | 0.3864 |
|
| 60 |
+
| 0.1086 | 22.02 | 2400 | 0.4568 | 0.3796 |
|
| 61 |
+
| 0.0998 | 25.69 | 2800 | 0.4687 | 0.3732 |
|
| 62 |
+
| 0.0863 | 29.36 | 3200 | 0.4726 | 0.3803 |
|
| 63 |
+
| 0.0809 | 33.03 | 3600 | 0.4479 | 0.3601 |
|
| 64 |
+
| 0.0747 | 36.7 | 4000 | 0.4624 | 0.3525 |
|
| 65 |
+
| 0.0692 | 40.37 | 4400 | 0.4366 | 0.3435 |
|
| 66 |
+
| 0.0595 | 44.04 | 4800 | 0.4204 | 0.3510 |
|
| 67 |
+
| 0.0584 | 47.71 | 5200 | 0.4202 | 0.3402 |
|
| 68 |
+
| 0.0545 | 51.38 | 5600 | 0.4366 | 0.3343 |
|
| 69 |
+
| 0.0486 | 55.05 | 6000 | 0.4492 | 0.3678 |
|
| 70 |
+
| 0.0444 | 58.72 | 6400 | 0.4471 | 0.3301 |
|
| 71 |
+
| 0.0406 | 62.39 | 6800 | 0.4382 | 0.3318 |
|
| 72 |
+
| 0.0341 | 66.06 | 7200 | 0.4295 | 0.3258 |
|
| 73 |
+
| 0.0297 | 69.72 | 7600 | 0.4336 | 0.3205 |
|
| 74 |
+
| 0.0295 | 73.39 | 8000 | 0.4240 | 0.3199 |
|
| 75 |
+
| 0.0261 | 77.06 | 8400 | 0.4316 | 0.3143 |
|
| 76 |
+
| 0.0247 | 80.73 | 8800 | 0.4300 | 0.3165 |
|
| 77 |
+
| 0.0207 | 84.4 | 9200 | 0.4380 | 0.3111 |
|
| 78 |
+
| 0.0203 | 88.07 | 9600 | 0.4218 | 0.2998 |
|
| 79 |
+
| 0.0174 | 91.74 | 10000 | 0.4271 | 0.2973 |
|
| 80 |
+
| 0.015 | 95.41 | 10400 | 0.4330 | 0.2939 |
|
| 81 |
+
| 0.0144 | 99.08 | 10800 | 0.4316 | 0.2905 |
|
| 82 |
|
| 83 |
|
| 84 |
### Framework versions
|
| 85 |
|
| 86 |
+
- Transformers 4.23.1
|
| 87 |
+
- Pytorch 1.12.1+cu102
|
| 88 |
- Datasets 2.5.2
|
| 89 |
- Tokenizers 0.13.1
|