Update README.md
Browse files
README.md
CHANGED
@@ -2,20 +2,46 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: openai/whisper-tiny
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
metrics:
|
7 |
- wer
|
|
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
#
|
17 |
|
18 |
-
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.3628
|
21 |
- Wer Ortho: 34.7985
|
@@ -69,4 +95,4 @@ The following hyperparameters were used during training:
|
|
69 |
- Transformers 4.36.2
|
70 |
- Pytorch 2.1.0+cu121
|
71 |
- Datasets 2.16.0
|
72 |
-
- Tokenizers 0.15.0
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: openai/whisper-tiny
|
4 |
tags:
|
5 |
+
- hf-asr-leaderboard
|
6 |
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- mozilla-foundation/common_voice_16_0
|
9 |
+
language:
|
10 |
+
- hu
|
11 |
+
widget:
|
12 |
+
- example_title: Sample 1
|
13 |
+
src: https://huggingface.co/datasets/Hungarians/samples/resolve/main/Sample1.flac
|
14 |
+
- example_title: Sample 2
|
15 |
+
src: https://huggingface.co/datasets/Hungarians/samples/resolve/main/Sample2.flac
|
16 |
metrics:
|
17 |
- wer
|
18 |
+
pipeline_tag: automatic-speech-recognition
|
19 |
model-index:
|
20 |
+
- name: Whisper Tiny Hungarian
|
21 |
+
results:
|
22 |
+
- task:
|
23 |
+
name: Automatic Speech Recognition
|
24 |
+
type: automatic-speech-recognition
|
25 |
+
dataset:
|
26 |
+
name: Common Voice 16.0 - Hungarian
|
27 |
+
type: mozilla-foundation/common_voice_16_0
|
28 |
+
config: hu
|
29 |
+
split: test
|
30 |
+
args: hu
|
31 |
+
metrics:
|
32 |
+
- name: Wer
|
33 |
+
type: wer
|
34 |
+
value: 32.2247
|
35 |
+
verified: true
|
36 |
+
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
should probably proofread and complete it, then remove this comment. -->
|
41 |
|
42 |
+
# Whisper Tiny Hungarian
|
43 |
|
44 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 16 dataset of Mozilla Foundation.
|
45 |
It achieves the following results on the evaluation set:
|
46 |
- Loss: 0.3628
|
47 |
- Wer Ortho: 34.7985
|
|
|
95 |
- Transformers 4.36.2
|
96 |
- Pytorch 2.1.0+cu121
|
97 |
- Datasets 2.16.0
|
98 |
+
- Tokenizers 0.15.0
|