Commit
•
01c6843
1
Parent(s):
297a301
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- thennal/IMaSC
|
5 |
+
language:
|
6 |
+
- ml
|
7 |
+
model-index:
|
8 |
+
- name: Malwhisper-v1-medium - Kurian Benoy
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
type: automatic-speech-recognition
|
12 |
+
name: Automatic Speech Recognition
|
13 |
+
dataset:
|
14 |
+
name: Common Voice 11.0
|
15 |
+
type: mozilla-foundation/common_voice_11_0
|
16 |
+
config: ml
|
17 |
+
split: test
|
18 |
+
args: ml
|
19 |
+
metrics:
|
20 |
+
- type: wer
|
21 |
+
value: 23.69
|
22 |
+
name: WER
|
23 |
+
- type: cer
|
24 |
+
value: 12.17
|
25 |
+
name: CER
|
26 |
+
library_name: transformers
|
27 |
+
---
|
28 |
+
|
29 |
+
## Malwhisper-v1-small
|
30 |
+
|
31 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) fine-tuned on [IMASc dataset](https://www.kaggle.com/datasets/thennal/imasc).
|
32 |
+
|
33 |
+
IMaSC is a Malayalam text and speech corpus made available by ICFOSS for the purpose of developing speech technology for Malayalam, particularly text-to-speech. The corpus contains 34,473 text-audio pairs of Malayalam sentences spoken by 8 speakers, totalling in approximately 50 hours of audio.
|
34 |
+
|
35 |
+
The fine-tuned model on evaluating in the following dataset:
|
36 |
+
|
37 |
+
**In Mozilla CommonVoice 11.0 dataset (Malayalam subset):**
|
38 |
+
|
39 |
+
WER - 23.69
|
40 |
+
|
41 |
+
CER - 12.17
|
42 |
+
|
43 |
+
**In SMC Malayalam Speech Corpus dataset:**
|
44 |
+
|
45 |
+
WER - 23.8
|
46 |
+
|
47 |
+
CER - 12.63
|