update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 0.
|
| 18 |
-
- Wer: 0.
|
| 19 |
-
- Cer: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -44,30 +44,39 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 2000
|
| 47 |
-
- training_steps:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 53 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 54 |
-
| 2.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.2536
|
| 18 |
+
- Wer: 0.5805
|
| 19 |
+
- Cer: 0.0690
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 2000
|
| 47 |
+
- training_steps: 26000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 53 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 54 |
+
| 2.0464 | 1.49 | 1000 | 1.5865 | 0.9968 | 0.5743 |
|
| 55 |
+
| 1.2779 | 2.98 | 2000 | 0.4195 | 0.7539 | 0.1008 |
|
| 56 |
+
| 1.0865 | 4.46 | 3000 | 0.3272 | 0.6791 | 0.0852 |
|
| 57 |
+
| 1.0852 | 5.95 | 4000 | 0.3039 | 0.6409 | 0.0789 |
|
| 58 |
+
| 1.0193 | 7.44 | 5000 | 0.3009 | 0.6442 | 0.0809 |
|
| 59 |
+
| 0.9566 | 8.93 | 6000 | 0.2804 | 0.6182 | 0.0762 |
|
| 60 |
+
| 0.9086 | 10.42 | 7000 | 0.2842 | 0.6336 | 0.0772 |
|
| 61 |
+
| 0.9161 | 11.9 | 8000 | 0.2757 | 0.6044 | 0.0735 |
|
| 62 |
+
| 0.8569 | 13.39 | 9000 | 0.2809 | 0.6052 | 0.0748 |
|
| 63 |
+
| 0.8517 | 14.88 | 10000 | 0.2813 | 0.6166 | 0.0759 |
|
| 64 |
+
| 0.8304 | 16.37 | 11000 | 0.2808 | 0.6044 | 0.0759 |
|
| 65 |
+
| 0.8325 | 17.86 | 12000 | 0.2656 | 0.6060 | 0.0735 |
|
| 66 |
+
| 0.7918 | 19.35 | 13000 | 0.2676 | 0.5930 | 0.0730 |
|
| 67 |
+
| 0.8061 | 20.83 | 14000 | 0.2740 | 0.5890 | 0.0731 |
|
| 68 |
+
| 0.7206 | 22.32 | 15000 | 0.2735 | 0.6141 | 0.0730 |
|
| 69 |
+
| 0.7372 | 23.81 | 16000 | 0.2663 | 0.5857 | 0.0711 |
|
| 70 |
+
| 0.7285 | 25.3 | 17000 | 0.2708 | 0.5841 | 0.0723 |
|
| 71 |
+
| 0.6778 | 26.79 | 18000 | 0.2726 | 0.5825 | 0.0724 |
|
| 72 |
+
| 0.7117 | 28.27 | 19000 | 0.2737 | 0.5898 | 0.0723 |
|
| 73 |
+
| 0.6951 | 29.76 | 20000 | 0.2733 | 0.5890 | 0.0721 |
|
| 74 |
+
| 0.6775 | 31.25 | 21000 | 0.2721 | 0.5865 | 0.0725 |
|
| 75 |
+
| 0.666 | 32.74 | 22000 | 0.2733 | 0.5857 | 0.0721 |
|
| 76 |
+
| 0.688 | 34.23 | 23000 | 0.2700 | 0.5890 | 0.0718 |
|
| 77 |
+
| 0.6813 | 35.71 | 24000 | 0.2724 | 0.5930 | 0.0717 |
|
| 78 |
+
| 0.6409 | 37.2 | 25000 | 0.2704 | 0.5922 | 0.0714 |
|
| 79 |
+
| 0.6427 | 38.69 | 26000 | 0.2704 | 0.5881 | 0.0713 |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|