Joshua Rwanda commited on
Commit ·
ef0d353
1
Parent(s): 026394f
End of training
Browse files- README.md +6 -6
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- eval_loss: inf
|
| 21 |
-
- eval_wer: 0.
|
| 22 |
-
- eval_runtime:
|
| 23 |
-
- eval_samples_per_second:
|
| 24 |
-
- eval_steps_per_second: 1.
|
| 25 |
- epoch: 0.37
|
| 26 |
- step: 400
|
| 27 |
|
|
@@ -42,7 +42,7 @@ More information needed
|
|
| 42 |
### Training hyperparameters
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
-
- learning_rate: 0.
|
| 46 |
- train_batch_size: 16
|
| 47 |
- eval_batch_size: 8
|
| 48 |
- seed: 42
|
|
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
|
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_steps: 500
|
| 54 |
-
- num_epochs:
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 18 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- eval_loss: inf
|
| 21 |
+
- eval_wer: 0.5730
|
| 22 |
+
- eval_runtime: 1031.5347
|
| 23 |
+
- eval_samples_per_second: 10.926
|
| 24 |
+
- eval_steps_per_second: 1.366
|
| 25 |
- epoch: 0.37
|
| 26 |
- step: 400
|
| 27 |
|
|
|
|
| 42 |
### Training hyperparameters
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 0.0003
|
| 46 |
- train_batch_size: 16
|
| 47 |
- eval_batch_size: 8
|
| 48 |
- seed: 42
|
|
|
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_steps: 500
|
| 54 |
+
- num_epochs: 30
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
| 57 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1261934580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7aa1ddb1af385017bb9634cc3447b9e84a70eebad06e0aed6212adc00a272d5f
|
| 3 |
size 1261934580
|