hadiqa123
/

xlsr_ur_training

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

hadiqa123 commited on Sep 7, 2022

Commit

1cfaa0b

·

1 Parent(s): be98dff

update model card README.md

Files changed (1) hide show

README.md +12 -20

README.md CHANGED Viewed

@@ -16,8 +16,8 @@ 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 the common_voice_8_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2610
-- Wer: 0.7325
 ## Model description
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
 - num_epochs: 30
 - mixed_precision_training: Native AMP
@@ -50,23 +50,15 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 14.5044       | 1.69  | 100  | 3.9173          | 1.0    |
-| 3.3645        | 3.39  | 200  | 3.2475          | 1.0    |
-| 3.2318        | 5.08  | 300  | 3.2143          | 1.0    |
-| 3.1887        | 6.78  | 400  | 3.1672          | 1.0    |
-| 3.1233        | 8.47  | 500  | 3.0927          | 1.0    |
-| 3.0938        | 10.17 | 600  | 3.0836          | 0.9970 |
-| 3.0706        | 11.86 | 700  | 3.0319          | 0.9996 |
-| 2.9622        | 13.56 | 800  | 2.7973          | 0.9985 |
-| 2.6267        | 15.25 | 900  | 2.2553          | 0.9974 |
-| 1.9748        | 16.95 | 1000 | 1.6858          | 0.9170 |
-| 1.4739        | 18.64 | 1100 | 1.4620          | 0.8125 |
-| 1.2102        | 20.34 | 1200 | 1.3890          | 0.7779 |
-| 1.036         | 22.03 | 1300 | 1.3347          | 0.7672 |
-| 0.9462        | 23.73 | 1400 | 1.2970          | 0.7476 |
-| 0.8725        | 25.42 | 1500 | 1.2792          | 0.7461 |
-| 0.8374        | 27.12 | 1600 | 1.2574          | 0.7384 |
-| 0.7976        | 28.81 | 1700 | 1.2610          | 0.7325 |
 ### Framework versions

 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_8_0 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.8325
+- Wer: 0.4863
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
 - num_epochs: 30
 - mixed_precision_training: Native AMP
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 6.9537        | 3.25  | 1000 | 3.0940          | 0.9989 |
+| 2.1696        | 6.49  | 2000 | 0.9705          | 0.6830 |
+| 0.8637        | 9.74  | 3000 | 0.8098          | 0.5919 |
+| 0.6297        | 12.99 | 4000 | 0.8002          | 0.5469 |
+| 0.5034        | 16.23 | 5000 | 0.8019          | 0.5214 |
+| 0.4267        | 19.48 | 6000 | 0.8223          | 0.5085 |
+| 0.3847        | 22.73 | 7000 | 0.8081          | 0.4948 |
+| 0.342         | 25.97 | 8000 | 0.8300          | 0.4930 |
+| 0.3201        | 29.22 | 9000 | 0.8325          | 0.4863 |
 ### Framework versions