Model save
Browse files- README.md +36 -1
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -15,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# xlsr53
|
| 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 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -42,11 +45,43 @@ The following hyperparameters were used during training:
|
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- lr_scheduler_warmup_steps: 10
|
| 45 |
-
- num_epochs:
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
|
|
|
| 15 |
# xlsr53
|
| 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: 3.6497
|
| 20 |
+
- Cer: 1.0
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 45 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 10
|
| 48 |
+
- num_epochs: 30
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 86.7857 | 1.0 | 10 | 13.0096 | 0.9930 |
|
| 56 |
+
| 64.0349 | 2.0 | 20 | 5.7889 | 1.0 |
|
| 57 |
+
| 20.8761 | 3.0 | 30 | 4.3652 | 1.0 |
|
| 58 |
+
| 12.3363 | 4.0 | 40 | 3.8773 | 1.0 |
|
| 59 |
+
| 11.0137 | 5.0 | 50 | 3.7471 | 1.0 |
|
| 60 |
+
| 10.7147 | 6.0 | 60 | 3.6982 | 1.0 |
|
| 61 |
+
| 10.5702 | 7.0 | 70 | 3.6885 | 1.0 |
|
| 62 |
+
| 10.1350 | 8.0 | 80 | 3.6772 | 1.0 |
|
| 63 |
+
| 10.7296 | 9.0 | 90 | 3.6753 | 1.0 |
|
| 64 |
+
| 10.0155 | 10.0 | 100 | 3.6693 | 1.0 |
|
| 65 |
+
| 23.2533 | 11.0 | 110 | 3.6945 | 1.0 |
|
| 66 |
+
| 11.0381 | 12.0 | 120 | 3.6739 | 1.0 |
|
| 67 |
+
| 10.8187 | 13.0 | 130 | 3.6736 | 1.0 |
|
| 68 |
+
| 10.4372 | 14.0 | 140 | 3.6692 | 1.0 |
|
| 69 |
+
| 10.3977 | 15.0 | 150 | 3.6721 | 1.0 |
|
| 70 |
+
| 10.1144 | 16.0 | 160 | 3.6679 | 1.0 |
|
| 71 |
+
| 10.2825 | 17.0 | 170 | 3.6669 | 1.0 |
|
| 72 |
+
| 10.4510 | 18.0 | 180 | 3.6651 | 1.0 |
|
| 73 |
+
| 10.1287 | 19.0 | 190 | 3.6654 | 1.0 |
|
| 74 |
+
| 10.1370 | 20.0 | 200 | 3.6608 | 1.0 |
|
| 75 |
+
| 10.3325 | 21.0 | 210 | 3.6639 | 1.0 |
|
| 76 |
+
| 10.5143 | 22.0 | 220 | 3.6630 | 1.0 |
|
| 77 |
+
| 10.3311 | 23.0 | 230 | 3.6666 | 1.0 |
|
| 78 |
+
| 10.4097 | 24.0 | 240 | 3.6611 | 1.0 |
|
| 79 |
+
| 13.4818 | 25.0 | 250 | 3.6602 | 1.0 |
|
| 80 |
+
| 13.6625 | 26.0 | 260 | 3.6586 | 1.0 |
|
| 81 |
+
| 10.1651 | 27.0 | 270 | 3.6568 | 1.0 |
|
| 82 |
+
| 10.3636 | 28.0 | 280 | 3.6508 | 1.0 |
|
| 83 |
+
| 13.1884 | 29.0 | 290 | 3.6498 | 1.0 |
|
| 84 |
+
| 9.9916 | 30.0 | 300 | 3.6497 | 1.0 |
|
| 85 |
|
| 86 |
|
| 87 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262213332
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22f25dae6b7abd5ec82afce04af5f0677752113609b884cc951b8a6aaeaf202d
|
| 3 |
size 1262213332
|