Commit
·
af2e8fe
1
Parent(s):
3b8634f
update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 0.
|
| 18 |
-
- Wer: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -48,40 +48,40 @@ The following hyperparameters were used during training:
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 50 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 51 |
-
| 3.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 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 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|
| 83 |
|
| 84 |
-
- Transformers 4.
|
| 85 |
- Pytorch 1.11.0+cu113
|
| 86 |
-
- Datasets 1.
|
| 87 |
- Tokenizers 0.12.1
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.5322
|
| 18 |
+
- Wer: 0.3323
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 50 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 51 |
+
| 3.5758 | 1.0 | 500 | 1.8895 | 1.0011 |
|
| 52 |
+
| 0.8598 | 2.01 | 1000 | 0.5127 | 0.5265 |
|
| 53 |
+
| 0.4207 | 3.01 | 1500 | 0.4336 | 0.4461 |
|
| 54 |
+
| 0.2885 | 4.02 | 2000 | 0.4399 | 0.4348 |
|
| 55 |
+
| 0.2247 | 5.02 | 2500 | 0.4028 | 0.4017 |
|
| 56 |
+
| 0.1805 | 6.02 | 3000 | 0.4152 | 0.3955 |
|
| 57 |
+
| 0.1559 | 7.03 | 3500 | 0.4564 | 0.3862 |
|
| 58 |
+
| 0.133 | 8.03 | 4000 | 0.4411 | 0.3754 |
|
| 59 |
+
| 0.1204 | 9.04 | 4500 | 0.4474 | 0.3726 |
|
| 60 |
+
| 0.1027 | 10.04 | 5000 | 0.4354 | 0.3625 |
|
| 61 |
+
| 0.0954 | 11.04 | 5500 | 0.4386 | 0.3622 |
|
| 62 |
+
| 0.0875 | 12.05 | 6000 | 0.4494 | 0.3603 |
|
| 63 |
+
| 0.0815 | 13.05 | 6500 | 0.4880 | 0.3612 |
|
| 64 |
+
| 0.0722 | 14.06 | 7000 | 0.5057 | 0.3626 |
|
| 65 |
+
| 0.0664 | 15.06 | 7500 | 0.4869 | 0.3560 |
|
| 66 |
+
| 0.0588 | 16.06 | 8000 | 0.5364 | 0.3609 |
|
| 67 |
+
| 0.0595 | 17.07 | 8500 | 0.5300 | 0.3528 |
|
| 68 |
+
| 0.0538 | 18.07 | 9000 | 0.5287 | 0.3570 |
|
| 69 |
+
| 0.0462 | 19.08 | 9500 | 0.5485 | 0.3536 |
|
| 70 |
+
| 0.0411 | 20.08 | 10000 | 0.4889 | 0.3500 |
|
| 71 |
+
| 0.0395 | 21.08 | 10500 | 0.5098 | 0.3415 |
|
| 72 |
+
| 0.0362 | 22.09 | 11000 | 0.5488 | 0.3444 |
|
| 73 |
+
| 0.0299 | 23.09 | 11500 | 0.5159 | 0.3411 |
|
| 74 |
+
| 0.0326 | 24.1 | 12000 | 0.5515 | 0.3431 |
|
| 75 |
+
| 0.0269 | 25.1 | 12500 | 0.4999 | 0.3353 |
|
| 76 |
+
| 0.0245 | 26.1 | 13000 | 0.5197 | 0.3395 |
|
| 77 |
+
| 0.0242 | 27.11 | 13500 | 0.5218 | 0.3360 |
|
| 78 |
+
| 0.0214 | 28.11 | 14000 | 0.5646 | 0.3367 |
|
| 79 |
+
| 0.0219 | 29.12 | 14500 | 0.5322 | 0.3323 |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|
| 83 |
|
| 84 |
+
- Transformers 4.19.4
|
| 85 |
- Pytorch 1.11.0+cu113
|
| 86 |
+
- Datasets 1.13.3
|
| 87 |
- Tokenizers 0.12.1
|