update model card README.md
Browse files
README.md
CHANGED
|
@@ -6,8 +6,6 @@ tags:
|
|
| 6 |
- automatic-speech-recognition
|
| 7 |
- mozilla-foundation/common_voice_7_0
|
| 8 |
- generated_from_trainer
|
| 9 |
-
- sv
|
| 10 |
-
- robust-speech-event
|
| 11 |
datasets:
|
| 12 |
- common_voice
|
| 13 |
model-index:
|
|
@@ -22,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 22 |
|
| 23 |
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UR dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
-
- Loss:
|
| 26 |
-
- Wer:
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -43,16 +41,20 @@ More information needed
|
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
- learning_rate: 0.0003
|
| 46 |
-
- train_batch_size:
|
| 47 |
- eval_batch_size: 8
|
| 48 |
- seed: 42
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
-
- training_steps:
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
|
|
|
| 6 |
- automatic-speech-recognition
|
| 7 |
- mozilla-foundation/common_voice_7_0
|
| 8 |
- generated_from_trainer
|
|
|
|
|
|
|
| 9 |
datasets:
|
| 10 |
- common_voice
|
| 11 |
model-index:
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UR dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.5614
|
| 24 |
+
- Wer: 0.6765
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
- learning_rate: 0.0003
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
- eval_batch_size: 8
|
| 46 |
- seed: 42
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
+
- training_steps: 1000
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 56 |
+
| 1.9115 | 20.83 | 500 | 1.5400 | 0.7280 |
|
| 57 |
+
| 0.1155 | 41.67 | 1000 | 1.5614 | 0.6765 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|