Commit
•
40a44f3
1
Parent(s):
46e6da5
update model card README.md
Browse files
README.md
CHANGED
@@ -11,19 +11,20 @@ metrics:
|
|
11 |
- wer
|
12 |
model-index:
|
13 |
- name: Whisper Small Hi - Swedish
|
14 |
-
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
name: Common Voice 11.0
|
20 |
type: mozilla-foundation/common_voice_11_0
|
|
|
21 |
split: None
|
22 |
-
args: 'config:
|
23 |
metrics:
|
24 |
- name: Wer
|
25 |
type: wer
|
26 |
-
value:
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -33,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
|
34 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
-
- Loss:
|
37 |
-
- Wer:
|
38 |
|
39 |
## Model description
|
40 |
|
@@ -53,25 +54,27 @@ More information needed
|
|
53 |
### Training hyperparameters
|
54 |
|
55 |
The following hyperparameters were used during training:
|
56 |
-
- learning_rate:
|
57 |
- train_batch_size: 16
|
58 |
- eval_batch_size: 8
|
59 |
- seed: 42
|
60 |
-
- optimizer: Adam with betas=(0.9,0.
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_steps: 500
|
63 |
-
- training_steps:
|
64 |
-
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
-
|
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
|
|
|
|
|
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
11 |
- wer
|
12 |
model-index:
|
13 |
- name: Whisper Small Hi - Swedish
|
14 |
+
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
name: Common Voice 11.0
|
20 |
type: mozilla-foundation/common_voice_11_0
|
21 |
+
config: null
|
22 |
split: None
|
23 |
+
args: 'config: hi, split: test'
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
+
value: 19.647226479524615
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.3953
|
38 |
+
- Wer: 19.6472
|
39 |
|
40 |
## Model description
|
41 |
|
|
|
54 |
### Training hyperparameters
|
55 |
|
56 |
The following hyperparameters were used during training:
|
57 |
+
- learning_rate: 1e-05
|
58 |
- train_batch_size: 16
|
59 |
- eval_batch_size: 8
|
60 |
- seed: 42
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|
64 |
+
- training_steps: 1
|
|
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
+
| 0.1331 | 1.29 | 1000 | 0.3014 | 22.3602 |
|
71 |
+
| 0.0537 | 2.59 | 2000 | 0.2988 | 20.8572 |
|
72 |
+
| 0.0217 | 3.88 | 3000 | 0.3093 | 20.5641 |
|
73 |
+
| 0.004 | 5.17 | 4000 | 0.3551 | 20.0479 |
|
74 |
+
| 0.0015 | 6.47 | 5000 | 0.3701 | 20.0022 |
|
75 |
+
| 0.0015 | 7.76 | 6000 | 0.3769 | 19.7386 |
|
76 |
+
| 0.0007 | 9.06 | 7000 | 0.3908 | 19.7010 |
|
77 |
+
| 0.0006 | 10.35 | 8000 | 0.3953 | 19.6472 |
|
78 |
|
79 |
|
80 |
### Framework versions
|