noflm
commited on
Commit
•
ea7fd5b
1
Parent(s):
a8c33b6
update model card README.md
Browse files
README.md
CHANGED
@@ -1,41 +1,38 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- ja
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
-
- whisper-event
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
13 |
-
- name:
|
14 |
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
-
name:
|
20 |
-
type:
|
21 |
config: ja
|
22 |
split: test
|
23 |
args: ja
|
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
|
31 |
should probably proofread and complete it, then remove this comment. -->
|
32 |
|
33 |
-
#
|
34 |
|
35 |
-
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Wer:
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -55,25 +52,34 @@ More information needed
|
|
55 |
|
56 |
The following hyperparameters were used during training:
|
57 |
- learning_rate: 1e-05
|
58 |
-
- train_batch_size:
|
59 |
-
- eval_batch_size:
|
60 |
- seed: 42
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: constant_with_warmup
|
63 |
-
- lr_scheduler_warmup_steps:
|
64 |
-
- training_steps:
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
-
| Training Loss | Epoch | Step
|
70 |
-
|
71 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
75 |
|
76 |
- Transformers 4.26.0.dev0
|
77 |
-
- Pytorch 1.13.
|
78 |
- Datasets 2.8.1.dev0
|
79 |
- Tokenizers 0.13.2
|
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
+
- common_voice_11_0
|
7 |
metrics:
|
8 |
- wer
|
9 |
model-index:
|
10 |
+
- name: whisper-base-ja-cv11
|
11 |
results:
|
12 |
- task:
|
13 |
name: Automatic Speech Recognition
|
14 |
type: automatic-speech-recognition
|
15 |
dataset:
|
16 |
+
name: common_voice_11_0
|
17 |
+
type: common_voice_11_0
|
18 |
config: ja
|
19 |
split: test
|
20 |
args: ja
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 21.991788980318223
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
should probably proofread and complete it, then remove this comment. -->
|
29 |
|
30 |
+
# whisper-base-ja-cv11
|
31 |
|
32 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice_11_0 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.6532
|
35 |
+
- Wer: 21.9918
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 1e-05
|
55 |
+
- train_batch_size: 32
|
56 |
+
- eval_batch_size: 16
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: constant_with_warmup
|
60 |
+
- lr_scheduler_warmup_steps: 500
|
61 |
+
- training_steps: 10000
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
68 |
+
| 0.3273 | 3.02 | 1000 | 0.4225 | 20.8253 |
|
69 |
+
| 0.0923 | 7.0 | 2000 | 0.4643 | 21.2200 |
|
70 |
+
| 0.0164 | 10.02 | 3000 | 0.5403 | 22.9627 |
|
71 |
+
| 0.006 | 14.01 | 4000 | 0.5820 | 21.0861 |
|
72 |
+
| 0.0046 | 17.02 | 5000 | 0.5852 | 22.0728 |
|
73 |
+
| 0.0034 | 21.01 | 6000 | 0.6113 | 21.6623 |
|
74 |
+
| 0.0028 | 24.03 | 7000 | 0.6582 | 22.3266 |
|
75 |
+
| 0.0025 | 28.01 | 8000 | 0.6350 | 22.2332 |
|
76 |
+
| 0.0029 | 32.0 | 9000 | 0.6468 | 22.1098 |
|
77 |
+
| 0.0014 | 35.02 | 10000 | 0.6532 | 21.9918 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.26.0.dev0
|
83 |
+
- Pytorch 1.13.1+cu117
|
84 |
- Datasets 2.8.1.dev0
|
85 |
- Tokenizers 0.13.2
|