bjelkenhed
commited on
Commit
•
c159e0b
1
Parent(s):
12b0b8c
update model card README.md
Browse files
README.md
CHANGED
@@ -1,41 +1,38 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- sv
|
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: sv-SE
|
22 |
split: test
|
23 |
args: sv-SE
|
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-large-v2](https://huggingface.co/openai/whisper-large-v2) on the
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss:
|
38 |
-
- Wer:
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -63,15 +60,18 @@ The following hyperparameters were used during training:
|
|
63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
- lr_scheduler_type: linear
|
65 |
- lr_scheduler_warmup_steps: 500
|
66 |
-
- training_steps:
|
67 |
- mixed_precision_training: Native AMP
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
72 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
73 |
-
|
|
74 |
-
|
|
|
|
|
|
|
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
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: openai/whisper-large-v2
|
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: sv-SE
|
19 |
split: test
|
20 |
args: sv-SE
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 9.220639613007256
|
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 |
+
# openai/whisper-large-v2
|
31 |
|
32 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_11_0 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.2337
|
35 |
+
- Wer: 9.2206
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_steps: 500
|
63 |
+
- training_steps: 5000
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
+
| 0.0695 | 0.2 | 1000 | 0.2695 | 12.4671 |
|
71 |
+
| 0.0524 | 0.4 | 2000 | 0.2659 | 11.6367 |
|
72 |
+
| 0.046 | 0.6 | 3000 | 0.2402 | 10.6557 |
|
73 |
+
| 0.0342 | 0.8 | 4000 | 0.2339 | 10.1774 |
|
74 |
+
| 0.0224 | 1.14 | 5000 | 0.2337 | 9.2206 |
|
75 |
|
76 |
|
77 |
### Framework versions
|