End of training
Browse files- README.md +8 -8
- pytorch_model.bin +1 -1
README.md
CHANGED
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
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:
|
21 |
-
- eval_wer: 0.
|
22 |
-
- eval_runtime:
|
23 |
-
- eval_samples_per_second:
|
24 |
-
- eval_steps_per_second: 2.
|
25 |
-
- epoch:
|
26 |
-
- step:
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
|
|
50 |
- total_train_batch_size: 32
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
-
- lr_scheduler_warmup_steps:
|
54 |
- num_epochs: 30
|
55 |
|
56 |
### Framework versions
|
|
|
17 |
|
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: 1.5610
|
21 |
+
- eval_wer: 0.9291
|
22 |
+
- eval_runtime: 39.0397
|
23 |
+
- eval_samples_per_second: 20.774
|
24 |
+
- eval_steps_per_second: 2.613
|
25 |
+
- epoch: 26.01
|
26 |
+
- step: 13200
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
50 |
- total_train_batch_size: 32
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
+
- lr_scheduler_warmup_steps: 100
|
54 |
- num_epochs: 30
|
55 |
|
56 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262135533
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e80f2f06c0a4c01bfcb11cca8cecd704352978cec51dff7849f71018bf4cfca9
|
3 |
size 1262135533
|