Commit
•
c9b6f4c
1
Parent(s):
76a06fd
End of training
Browse files
README.md
CHANGED
@@ -24,7 +24,7 @@ model-index:
|
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
-
value:
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
34 |
|
35 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Wer:
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -67,16 +67,16 @@ The following hyperparameters were used during training:
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
-
| 0.
|
71 |
-
| 0.0 | 40.0 | 2000 | 0.
|
72 |
-
| 0.0 | 60.0 | 3000 | 0.
|
73 |
-
| 0.0 | 80.0 | 4000 | 0.
|
74 |
-
| 0.0 | 100.0 | 5000 | 0.
|
75 |
|
76 |
|
77 |
### Framework versions
|
78 |
|
79 |
- Transformers 4.41.0
|
80 |
-
- Pytorch 2.
|
81 |
- Datasets 2.19.1
|
82 |
- Tokenizers 0.19.1
|
|
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
+
value: 58.44155844155844
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.9705
|
38 |
+
- Wer: 58.4416
|
39 |
|
40 |
## Model description
|
41 |
|
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
+
| 0.0021 | 20.0 | 1000 | 0.8610 | 61.0390 |
|
71 |
+
| 0.0 | 40.0 | 2000 | 0.9097 | 59.7403 |
|
72 |
+
| 0.0 | 60.0 | 3000 | 0.9417 | 59.7403 |
|
73 |
+
| 0.0 | 80.0 | 4000 | 0.9622 | 59.7403 |
|
74 |
+
| 0.0 | 100.0 | 5000 | 0.9705 | 58.4416 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
78 |
|
79 |
- Transformers 4.41.0
|
80 |
+
- Pytorch 2.3.0+cu121
|
81 |
- Datasets 2.19.1
|
82 |
- Tokenizers 0.19.1
|