Commit
•
f3b7c54
1
Parent(s):
57712e5
End of training
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ model-index:
|
|
20 |
metrics:
|
21 |
- name: Wer
|
22 |
type: wer
|
23 |
-
value: 0.
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
This model was trained from scratch on the common_voice_13_0 dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss: 0.
|
34 |
-
- Wer: 0.
|
35 |
-
- Cer: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -57,7 +57,7 @@ The following hyperparameters were used during training:
|
|
57 |
- seed: 42
|
58 |
- gradient_accumulation_steps: 2
|
59 |
- total_train_batch_size: 16
|
60 |
-
- optimizer: Adam with betas=(0.
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_ratio: 0.1
|
63 |
- num_epochs: 5
|
@@ -67,11 +67,11 @@ The following hyperparameters were used during training:
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
70 |
-
|
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
20 |
metrics:
|
21 |
- name: Wer
|
22 |
type: wer
|
23 |
+
value: 0.49680838717165077
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
This model was trained from scratch on the common_voice_13_0 dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 0.6632
|
34 |
+
- Wer: 0.4968
|
35 |
+
- Cer: 0.2099
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
57 |
- seed: 42
|
58 |
- gradient_accumulation_steps: 2
|
59 |
- total_train_batch_size: 16
|
60 |
+
- optimizer: Adam with betas=(0.85,0.9) and epsilon=1e-08
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_ratio: 0.1
|
63 |
- num_epochs: 5
|
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
70 |
+
| 1.9625 | 1.0 | 341 | 0.7371 | 0.5348 | 0.2190 |
|
71 |
+
| 0.2156 | 2.0 | 683 | 0.7057 | 0.5103 | 0.2169 |
|
72 |
+
| 0.2451 | 3.0 | 1024 | 0.6654 | 0.5161 | 0.2214 |
|
73 |
+
| 0.199 | 4.0 | 1366 | 0.6707 | 0.5089 | 0.2153 |
|
74 |
+
| 0.1657 | 4.99 | 1705 | 0.6632 | 0.4968 | 0.2099 |
|
75 |
|
76 |
|
77 |
### Framework versions
|