update model card README.md
Browse files
README.md
CHANGED
@@ -1,39 +1,38 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
-
- whisper-event
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
-
|
8 |
metrics:
|
9 |
- wer
|
10 |
model-index:
|
11 |
-
- name:
|
12 |
results:
|
13 |
- task:
|
14 |
name: Automatic Speech Recognition
|
15 |
type: automatic-speech-recognition
|
16 |
dataset:
|
17 |
-
name:
|
18 |
-
type:
|
19 |
config: 'no'
|
20 |
split: validation
|
21 |
args: 'no'
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
-
value:
|
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 |
-
#
|
32 |
|
33 |
-
This model is a fine-tuned version of [
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Wer:
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -60,19 +59,16 @@ The following hyperparameters were used during training:
|
|
60 |
- total_train_batch_size: 128
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: constant_with_warmup
|
63 |
-
-
|
64 |
-
- training_steps: 5000
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.6803 | 0.8 | 4000 | 0.3364 | 16.5652 |
|
75 |
-
| 0.6557 | 1.0 | 5000 | 0.3290 | 16.0171 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
+
- ncc_s
|
7 |
metrics:
|
8 |
- wer
|
9 |
model-index:
|
10 |
+
- name: pere/whisper-small-nob-clr
|
11 |
results:
|
12 |
- task:
|
13 |
name: Automatic Speech Recognition
|
14 |
type: automatic-speech-recognition
|
15 |
dataset:
|
16 |
+
name: ncc_s
|
17 |
+
type: ncc_s
|
18 |
config: 'no'
|
19 |
split: validation
|
20 |
args: 'no'
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 15.012180267965894
|
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 |
+
# pere/whisper-small-nob-clr
|
31 |
|
32 |
+
This model is a fine-tuned version of [pere/whisper-small-nob-clr](https://huggingface.co/pere/whisper-small-nob-clr) on the ncc_s dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.3284
|
35 |
+
- Wer: 15.0122
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
59 |
- total_train_batch_size: 128
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: constant_with_warmup
|
62 |
+
- training_steps: 3000
|
|
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
69 |
+
| 0.5975 | 0.33 | 1000 | 0.3354 | 15.7734 |
|
70 |
+
| 0.5783 | 0.67 | 2000 | 0.3327 | 16.3520 |
|
71 |
+
| 0.5788 | 1.0 | 3000 | 0.3284 | 15.0122 |
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|