nikhil6041
commited on
Commit
•
a80b621
1
Parent(s):
809750b
update model card README.md
Browse files
README.md
CHANGED
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# wav2vec2-commonvoice-hindi
|
16 |
|
17 |
-
This model is a fine-tuned version of [
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
-
- Wer:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -40,20 +40,19 @@ The following hyperparameters were used during training:
|
|
40 |
- train_batch_size: 16
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
|
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 500
|
46 |
-
- num_epochs:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
52 |
-
|
53 |
-
|
|
54 |
-
| 3.4778 | 21.05 | 400 | 3.5174 | 1.0 |
|
55 |
-
| 3.5119 | 31.58 | 600 | 3.5362 | 1.0 |
|
56 |
-
| 3.5133 | 42.11 | 800 | 3.5371 | 1.0 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
14 |
|
15 |
# wav2vec2-commonvoice-hindi
|
16 |
|
17 |
+
This model is a fine-tuned version of [theainerd/Wav2Vec2-large-xlsr-hindi](https://huggingface.co/theainerd/Wav2Vec2-large-xlsr-hindi) on the common_voice dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.9825
|
20 |
+
- Wer: 0.6763
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
40 |
- train_batch_size: 16
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 32
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 500
|
48 |
+
- num_epochs: 30
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
+
| No log | 20.0 | 100 | 0.8801 | 0.6754 |
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|