update model card README.md
Browse files
README.md
CHANGED
@@ -1,42 +1,42 @@
|
|
1 |
---
|
2 |
language:
|
3 |
-
-
|
4 |
license: apache-2.0
|
5 |
-
base_model: openai/whisper-
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
13 |
-
- name: Whisper
|
14 |
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
-
name:
|
20 |
-
type:
|
21 |
-
config:
|
22 |
-
split:
|
23 |
-
args:
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
-
value: 0.
|
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
|
34 |
|
35 |
-
This model is a fine-tuned version of [openai/whisper-
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Wer Ortho: 0.
|
39 |
-
- Wer: 0.
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -70,7 +70,7 @@ The following hyperparameters were used during training:
|
|
70 |
|
71 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
72 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
73 |
-
| 0.
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
1 |
---
|
2 |
language:
|
3 |
+
- en-US
|
4 |
license: apache-2.0
|
5 |
+
base_model: openai/whisper-tiny
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- PolyAI/minds14
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
13 |
+
- name: Whisper Tiny en-US
|
14 |
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
+
name: PolyAI/minds14
|
20 |
+
type: PolyAI/minds14
|
21 |
+
config: en-US
|
22 |
+
split: train
|
23 |
+
args: en-US
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
+
value: 0.320973348783314
|
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 Tiny en-US
|
34 |
|
35 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.6575
|
38 |
+
- Wer Ortho: 0.3219
|
39 |
+
- Wer: 0.3210
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
70 |
|
71 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
72 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
73 |
+
| 0.0007 | 17.94 | 500 | 0.6575 | 0.3219 | 0.3210 |
|
74 |
|
75 |
|
76 |
### Framework versions
|