End of training
Browse files- README.md +1 -29
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -7,24 +7,9 @@ tags:
|
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_16_1
|
10 |
-
metrics:
|
11 |
-
- wer
|
12 |
model-index:
|
13 |
- name: Whisper Large v3 Turbo - Bahriddin Muminov
|
14 |
-
results:
|
15 |
-
- task:
|
16 |
-
name: Automatic Speech Recognition
|
17 |
-
type: automatic-speech-recognition
|
18 |
-
dataset:
|
19 |
-
name: Common Voice 16.1
|
20 |
-
type: mozilla-foundation/common_voice_16_1
|
21 |
-
config: uz
|
22 |
-
split: test
|
23 |
-
args: 'config: uz, split: test'
|
24 |
-
metrics:
|
25 |
-
- name: Wer
|
26 |
-
type: wer
|
27 |
-
value: 99.63288088608068
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -33,9 +18,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
# Whisper Large v3 Turbo - Bahriddin Muminov
|
34 |
|
35 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
|
36 |
-
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.3021
|
38 |
-
- Wer: 99.6329
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -64,16 +46,6 @@ The following hyperparameters were used during training:
|
|
64 |
- training_steps: 4000
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
-
### Training results
|
68 |
-
|
69 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
71 |
-
| 0.4875 | 0.33 | 1000 | 0.4542 | 72.0290 |
|
72 |
-
| 0.3835 | 0.66 | 2000 | 0.3775 | 100.0 |
|
73 |
-
| 0.3371 | 0.99 | 3000 | 0.3221 | 100.0 |
|
74 |
-
| 0.2244 | 1.32 | 4000 | 0.3021 | 99.6329 |
|
75 |
-
|
76 |
-
|
77 |
### Framework versions
|
78 |
|
79 |
- Transformers 4.37.2
|
|
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_16_1
|
|
|
|
|
10 |
model-index:
|
11 |
- name: Whisper Large v3 Turbo - Bahriddin Muminov
|
12 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
18 |
# Whisper Large v3 Turbo - Bahriddin Muminov
|
19 |
|
20 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
46 |
- training_steps: 4000
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
### Framework versions
|
50 |
|
51 |
- Transformers 4.37.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3235581408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4f0531bf268b0db8416c81887739b96b290fc2994caa093c18666e5b5ad0e83
|
3 |
size 3235581408
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3102c16b7e8b253e01e9077b7ce47787bdab76f108c45e1f1458ba33a496714d
|
3 |
size 4856
|