speech-seq2seq
/

wav2vec2-2-bert-large-no-adapter-frozen-enc

Automatic Speech Recognition

speech-encoder-decoder

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

sanchit-gandhi HF staff commited on Feb 15, 2022

Commit

11e9ce6

•

1 Parent(s): 3dd03b6

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model was trained from scratch on the librispeech_asr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.1883
-- Wer: 2.0039
 ## Model description
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 6.7101        | 0.28  | 500  | 6.8996          | 1.2137 |
-| 6.5466        | 0.56  | 1000 | 6.7531          | 1.4516 |
-| 6.1449        | 0.84  | 1500 | 6.6346          | 1.8296 |
-| 6.5299        | 1.12  | 2000 | 6.5735          | 1.9686 |
-| 6.6303        | 1.4   | 2500 | 6.6005          | 1.9392 |
-| 6.4568        | 1.68  | 3000 | 6.6191          | 1.9739 |
-| 6.4666        | 1.96  | 3500 | 7.4679          | 2.0081 |
-| 6.2546        | 2.24  | 4000 | 7.7967          | 1.9948 |
-| 6.4101        | 2.52  | 4500 | 8.1178          | 1.9956 |
-| 6.142         | 2.8   | 5000 | 9.1883          | 2.0039 |
 ### Framework versions

 This model was trained from scratch on the librispeech_asr dataset.
 It achieves the following results on the evaluation set:
+- Loss: 11.7664
+- Wer: 2.0133
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 5.171         | 0.28  | 500  | 8.6956          | 2.0055 |
+| 5.307         | 0.56  | 1000 | 8.5958          | 2.0096 |
+| 5.1449        | 0.84  | 1500 | 10.4208         | 2.0115 |
+| 6.1351        | 1.12  | 2000 | 10.2950         | 2.0059 |
+| 6.2997        | 1.4   | 2500 | 10.6762         | 2.0115 |
+| 6.1394        | 1.68  | 3000 | 10.9190         | 2.0110 |
+| 6.1868        | 1.96  | 3500 | 11.0166         | 2.0112 |
+| 5.9647        | 2.24  | 4000 | 11.4154         | 2.0141 |
+| 6.2202        | 2.52  | 4500 | 11.5837         | 2.0152 |
+| 5.9612        | 2.8   | 5000 | 11.7664         | 2.0133 |
 ### Framework versions