Model save

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
@@ -16,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6889
-- Wer: 0.9480
+- Loss: 0.4942
+- Wer: 0.3917
 
 ## Model description
 
@@ -38,48 +39,33 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
 - train_batch_size: 16
-- eval_batch_size: 128
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 600
-- training_steps: 6000
+- lr_scheduler_warmup_steps: 300
+- training_steps: 3000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| No log        | 0.0672 | 200  | 3.0784          | 1.0    |
-| No log        | 0.1344 | 400  | 2.9962          | 1.0    |
-| 4.6966        | 0.2016 | 600  | 3.0380          | 1.0    |
-| 4.6966        | 0.2688 | 800  | 2.9616          | 1.0    |
-| 3.0067        | 0.3360 | 1000 | 2.9147          | 1.0    |
-| 3.0067        | 0.4032 | 1200 | 2.9158          | 1.0    |
-| 3.0067        | 0.4704 | 1400 | 2.9126          | 1.0    |
-| 2.9095        | 0.5376 | 1600 | 2.8195          | 1.0    |
-| 2.9095        | 0.6048 | 1800 | 2.3190          | 0.9804 |
-| 2.3631        | 0.6720 | 2000 | 1.5925          | 0.9349 |
-| 2.3631        | 0.7392 | 2200 | 1.3529          | 0.8784 |
-| 2.3631        | 0.8065 | 2400 | 1.2185          | 0.8690 |
-| 1.3164        | 0.8737 | 2600 | 1.1746          | 0.8566 |
-| 1.3164        | 0.9409 | 2800 | 1.2047          | 0.8444 |
-| 1.2708        | 1.0081 | 3000 | 1.3975          | 0.8781 |
-| 1.2708        | 1.0753 | 3200 | 1.5273          | 0.9086 |
-| 1.2708        | 1.1425 | 3400 | 1.5937          | 0.9166 |
-| 1.5876        | 1.2097 | 3600 | 1.4998          | 0.9331 |
-| 1.5876        | 1.2769 | 3800 | 1.6366          | 0.9646 |
-| 1.6623        | 1.3441 | 4000 | 1.6667          | 0.9701 |
-| 1.6623        | 1.4113 | 4200 | 1.5727          | 0.9483 |
-| 1.6623        | 1.4785 | 4400 | 1.6119          | 0.9611 |
-| 1.6759        | 1.5457 | 4600 | 1.5941          | 0.9337 |
-| 1.6759        | 1.6129 | 4800 | 1.4534          | 0.9059 |
-| 1.5779        | 1.6801 | 5000 | 2.0221          | 0.9572 |
-| 1.5779        | 1.7473 | 5200 | 1.7697          | 0.9399 |
-| 1.5779        | 1.8145 | 5400 | 1.6657          | 0.9377 |
-| 1.775         | 1.8817 | 5600 | 1.7365          | 0.9714 |
-| 1.775         | 1.9489 | 5800 | 1.6953          | 0.9580 |
-| 1.7507        | 2.0161 | 6000 | 1.6889          | 0.9480 |
+| No log        | 0.0672 | 200  | 2.9830          | 1.0    |
+| No log        | 0.1344 | 400  | 1.5613          | 0.9658 |
+| 3.6118        | 0.2016 | 600  | 1.0701          | 0.7649 |
+| 3.6118        | 0.2688 | 800  | 0.8868          | 0.6947 |
+| 0.9333        | 0.3360 | 1000 | 0.7680          | 0.6071 |
+| 0.9333        | 0.4032 | 1200 | 0.7224          | 0.5454 |
+| 0.9333        | 0.4704 | 1400 | 0.6733          | 0.5122 |
+| 0.7446        | 0.5376 | 1600 | 0.6437          | 0.4966 |
+| 0.7446        | 0.6048 | 1800 | 0.6064          | 0.4774 |
+| 0.6579        | 0.6720 | 2000 | 0.5674          | 0.4461 |
+| 0.6579        | 0.7392 | 2200 | 0.5556          | 0.4325 |
+| 0.6579        | 0.8065 | 2400 | 0.5264          | 0.4180 |
+| 0.5823        | 0.8737 | 2600 | 0.5130          | 0.4022 |
+| 0.5823        | 0.9409 | 2800 | 0.4982          | 0.3936 |
+| 0.5426        | 1.0081 | 3000 | 0.4942          | 0.3917 |
 
 
 ### Framework versions