weekcircle
commited on
Commit
•
418c247
1
Parent(s):
d7c8fd0
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/mms-1b-l1107](https://huggingface.co/facebook/mms-1b-l1107) on the common_voice_13_0 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 7.
|
36 |
-
- Wer: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -53,21 +53,25 @@ More information needed
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.001
|
56 |
-
- train_batch_size:
|
57 |
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_steps: 100
|
62 |
-
- num_epochs:
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
-
|
|
69 |
-
| 5.
|
70 |
-
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
|
73 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 0.9859013091641491
|
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/mms-1b-l1107](https://huggingface.co/facebook/mms-1b-l1107) on the common_voice_13_0 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 7.8369
|
36 |
+
- Wer: 0.9859
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.001
|
56 |
+
- train_batch_size: 8
|
57 |
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_steps: 100
|
62 |
+
- num_epochs: 20
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
+
| 11.2038 | 2.63 | 100 | 7.7632 | 0.9869 |
|
69 |
+
| 5.9383 | 5.26 | 200 | 8.0920 | 0.9909 |
|
70 |
+
| 5.6379 | 7.89 | 300 | 7.8850 | 0.9930 |
|
71 |
+
| 5.0749 | 10.53 | 400 | 7.8490 | 0.9940 |
|
72 |
+
| 3.791 | 13.16 | 500 | 7.4713 | 0.9849 |
|
73 |
+
| 3.3555 | 15.79 | 600 | 7.6595 | 0.9799 |
|
74 |
+
| 2.5415 | 18.42 | 700 | 7.8369 | 0.9859 |
|
75 |
|
76 |
|
77 |
### Framework versions
|