update model card README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
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.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Wer: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -53,22 +53,29 @@ More information needed
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.0003
|
56 |
-
- train_batch_size:
|
57 |
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 2
|
60 |
-
- total_train_batch_size:
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|
64 |
-
- num_epochs:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
-
| 5.
|
71 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 0.5094757094757095
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
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.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.1240
|
36 |
+
- Wer: 0.5095
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.0003
|
56 |
+
- train_batch_size: 16
|
57 |
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 32
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|
64 |
+
- num_epochs: 30
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| 5.1179 | 3.12 | 400 | 1.3528 | 0.8758 |
|
71 |
+
| 0.8834 | 6.25 | 800 | 0.9791 | 0.6978 |
|
72 |
+
| 0.4513 | 9.38 | 1200 | 0.9412 | 0.6085 |
|
73 |
+
| 0.291 | 12.5 | 1600 | 1.0826 | 0.5874 |
|
74 |
+
| 0.2133 | 15.62 | 2000 | 1.0616 | 0.5589 |
|
75 |
+
| 0.1653 | 18.75 | 2400 | 1.0475 | 0.5519 |
|
76 |
+
| 0.1235 | 21.88 | 2800 | 1.0702 | 0.5293 |
|
77 |
+
| 0.0927 | 25.0 | 3200 | 1.1390 | 0.5219 |
|
78 |
+
| 0.0698 | 28.12 | 3600 | 1.1240 | 0.5095 |
|
79 |
|
80 |
|
81 |
### Framework versions
|