Commit
•
8e5a350
1
Parent(s):
f9f171b
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,22 +4,7 @@ datasets:
|
|
| 4 |
- thennal/IMaSC
|
| 5 |
language:
|
| 6 |
- ml
|
| 7 |
-
|
| 8 |
-
- name: Malwhisper-v1-small
|
| 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: 24.83
|
| 22 |
-
name: WER
|
| 23 |
library_name: transformers
|
| 24 |
---
|
| 25 |
|
|
@@ -41,14 +26,9 @@ IMaSC is a Malayalam text and speech corpus made available by ICFOSS for the pur
|
|
| 41 |
|
| 42 |
The fine-tuned model on evaluating in the following dataset:
|
| 43 |
|
| 44 |
-
**In Mozilla CommonVoice 11.0 dataset (Malayalam subset):**
|
| 45 |
-
|
| 46 |
-
WER - 24.83
|
| 47 |
-
|
| 48 |
-
CER - 12.84
|
| 49 |
|
| 50 |
**In SMC Malayalam Speech Corpus dataset:**
|
| 51 |
|
| 52 |
-
WER -
|
| 53 |
|
| 54 |
-
CER -
|
|
|
|
| 4 |
- thennal/IMaSC
|
| 5 |
language:
|
| 6 |
- ml
|
| 7 |
+
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
library_name: transformers
|
| 9 |
---
|
| 10 |
|
|
|
|
| 26 |
|
| 27 |
The fine-tuned model on evaluating in the following dataset:
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
**In SMC Malayalam Speech Corpus dataset:**
|
| 31 |
|
| 32 |
+
WER - 73.56
|
| 33 |
|
| 34 |
+
CER - 17.82
|