StormblessedKal
commited on
Commit
•
df9b18c
1
Parent(s):
06d6b93
End of training
Browse files- README.md +21 -0
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
4 |
base_model: openai/whisper-large-v3
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
|
|
7 |
model-index:
|
8 |
- name: no-voice-clone-large-finetune-test
|
9 |
results: []
|
@@ -16,6 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# no-voice-clone-large-finetune-test
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -46,6 +51,22 @@ The following hyperparameters were used during training:
|
|
46 |
- training_steps: 2500
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
### Framework versions
|
50 |
|
51 |
- Transformers 4.45.2
|
|
|
4 |
base_model: openai/whisper-large-v3
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
model-index:
|
10 |
- name: no-voice-clone-large-finetune-test
|
11 |
results: []
|
|
|
18 |
# no-voice-clone-large-finetune-test
|
19 |
|
20 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.4622
|
23 |
+
- Wer: 20.1897
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
51 |
- training_steps: 2500
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
57 |
+
|:-------------:|:-------:|:----:|:---------------:|:-------:|
|
58 |
+
| 0.0088 | 4.6729 | 250 | 0.5014 | 21.1681 |
|
59 |
+
| 0.0079 | 9.3458 | 500 | 0.5158 | 29.2321 |
|
60 |
+
| 0.0001 | 14.0187 | 750 | 0.4311 | 23.9253 |
|
61 |
+
| 0.0 | 18.6916 | 1000 | 0.4457 | 20.5752 |
|
62 |
+
| 0.0 | 23.3645 | 1250 | 0.4520 | 20.6048 |
|
63 |
+
| 0.0 | 28.0374 | 1500 | 0.4560 | 20.1897 |
|
64 |
+
| 0.0 | 32.7103 | 1750 | 0.4588 | 20.1601 |
|
65 |
+
| 0.0 | 37.3832 | 2000 | 0.4607 | 20.1304 |
|
66 |
+
| 0.0 | 42.0561 | 2250 | 0.4618 | 20.2490 |
|
67 |
+
| 0.0 | 46.7290 | 2500 | 0.4622 | 20.1897 |
|
68 |
+
|
69 |
+
|
70 |
### Framework versions
|
71 |
|
72 |
- Transformers 4.45.2
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4993448880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e412ef6c14476053b32c576406a5fbac4572b1eefd1a649662a1bb55accf3942
|
3 |
size 4993448880
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:737b759acca57943a989e840db61505b12b20bbbad86cd9d9afb6d24c069904b
|
3 |
size 1180663192
|