toshiouchiyama
commited on
Commit
•
9181caa
1
Parent(s):
4a919f9
update model card README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- ja
|
4 |
-
license: apache-2.0
|
5 |
tags:
|
6 |
- hf-asr-leaderboard
|
7 |
- generated_from_trainer
|
@@ -10,32 +9,31 @@ datasets:
|
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
13 |
-
- name: Whisper Small
|
14 |
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
-
name:
|
20 |
type: Specific-Person-Voice
|
21 |
config: null
|
22 |
split: None
|
23 |
-
args: 'config: ja, split: train'
|
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 |
-
# Whisper Small
|
34 |
|
35 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Wer:
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -61,14 +59,16 @@ The following hyperparameters were used during training:
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 5
|
64 |
-
- training_steps:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
-
| No log |
|
71 |
-
| No log |
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
1 |
---
|
2 |
language:
|
3 |
- ja
|
|
|
4 |
tags:
|
5 |
- hf-asr-leaderboard
|
6 |
- generated_from_trainer
|
|
|
9 |
metrics:
|
10 |
- wer
|
11 |
model-index:
|
12 |
+
- name: Whisper Small Ja - Tohio Uchiyama
|
13 |
results:
|
14 |
- task:
|
15 |
name: Automatic Speech Recognition
|
16 |
type: automatic-speech-recognition
|
17 |
dataset:
|
18 |
+
name: Specific-Person-Voice
|
19 |
type: Specific-Person-Voice
|
20 |
config: null
|
21 |
split: None
|
|
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 23.239436619718308
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
should probably proofread and complete it, then remove this comment. -->
|
30 |
|
31 |
+
# Whisper Small Ja - Tohio Uchiyama
|
32 |
|
33 |
+
This model is a fine-tuned version of [openai/whisper-small-ja](https://huggingface.co/openai/whisper-small-ja) on the Specific-Person-Voice dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.7645
|
36 |
+
- Wer: 23.2394
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_steps: 5
|
62 |
+
- training_steps: 40
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| No log | 1.43 | 10 | 1.2124 | 21.1268 |
|
69 |
+
| No log | 2.86 | 20 | 0.8283 | 884.5070 |
|
70 |
+
| 1.2688 | 4.29 | 30 | 0.7769 | 23.2394 |
|
71 |
+
| 1.2688 | 5.71 | 40 | 0.7645 | 23.2394 |
|
72 |
|
73 |
|
74 |
### Framework versions
|