Commit ·
a13c088
1
Parent(s): 8421a48
update model card README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss:
|
| 24 |
- Wer: 1.0
|
| 25 |
|
| 26 |
## Model description
|
|
@@ -48,12 +48,15 @@ The following hyperparameters were used during training:
|
|
| 48 |
- total_train_batch_size: 32
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
-
- lr_scheduler_warmup_steps:
|
| 52 |
-
- num_epochs:
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.9141
|
| 24 |
- Wer: 1.0
|
| 25 |
|
| 26 |
## Model description
|
|
|
|
| 48 |
- total_train_batch_size: 32
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 20
|
| 52 |
+
- num_epochs: 2.0
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 59 |
+
| 2.9357 | 1.45 | 500 | 2.9459 | 1.0 |
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|