Upload README.md
Browse files
README.md
CHANGED
@@ -7,17 +7,35 @@ tags:
|
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_11_0
|
|
|
|
|
10 |
model-index:
|
11 |
-
- name: whisper-fine-tuned-
|
12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
-
# whisper-fine-tuned-
|
19 |
|
20 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -48,6 +66,17 @@ The following hyperparameters were used during training:
|
|
48 |
- training_steps: 5000
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
### Framework versions
|
52 |
|
53 |
- Transformers 4.27.0.dev0
|
|
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_11_0
|
10 |
+
metrics:
|
11 |
+
- wer
|
12 |
model-index:
|
13 |
+
- name: whisper-fine-tuned-de_arga
|
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: de
|
22 |
+
split: validation[2000:4000]
|
23 |
+
args: 'config: german, split: test'
|
24 |
+
metrics:
|
25 |
+
- name: Wer
|
26 |
+
type: wer
|
27 |
+
value: 13.547131036720566
|
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-fine-tuned-de_arga
|
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: 0.3381
|
38 |
+
- Wer: 13.5471
|
39 |
|
40 |
## Model description
|
41 |
|
|
|
66 |
- training_steps: 5000
|
67 |
- mixed_precision_training: Native AMP
|
68 |
|
69 |
+
### Training results
|
70 |
+
|
71 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
72 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
73 |
+
| 0.1278 | 1.6 | 1000 | 0.2690 | 13.9852 |
|
74 |
+
| 0.0155 | 3.2 | 2000 | 0.3036 | 13.5417 |
|
75 |
+
| 0.0035 | 4.8 | 3000 | 0.3180 | 13.4985 |
|
76 |
+
| 0.0012 | 6.4 | 4000 | 0.3335 | 13.5634 |
|
77 |
+
| 0.001 | 8.0 | 5000 | 0.3381 | 13.5471 |
|
78 |
+
|
79 |
+
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.27.0.dev0
|