juliensimon
/

wav2vec2-conformer-rel-pos-large-finetuned-speech-commands

Audio Classification

wav2vec2-conformer

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

Julien Simon commited on Jun 25, 2022

Commit

0763a50

·

1 Parent(s): 2559184

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -49,7 +49,7 @@ The model can spot one of the following keywords: "Yes", "No", "Up", "Down", "Le
 TBD
-###Training hyperparameters
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
@@ -63,7 +63,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
-### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
@@ -79,7 +79,7 @@ The following hyperparameters were used during training:
 | 0.7975        | 10.0  | 830  | 0.5256          | 0.9721   |
-### Framework versions
 - Transformers 4.20.1
 - Pytorch 1.11.0+cu102

 TBD
+#### Training hyperparameters
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
+#### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
 | 0.7975        | 10.0  | 830  | 0.5256          | 0.9721   |
+#### Framework versions
 - Transformers 4.20.1
 - Pytorch 1.11.0+cu102