Commit
·
b83d721
1
Parent(s):
83f2361
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: yashcode00/wav2vec2-large-xlsr-indian-language-classification-featureExtractor
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
|
@@ -22,11 +24,12 @@ It achieves the following results on the evaluation set:
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
-
|
|
|
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
|
|
|
|
| 3 |
base_model: yashcode00/wav2vec2-large-xlsr-indian-language-classification-featureExtractor
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
- This model is fully trained on the sample-Data of 11 languages provided
|
| 7 |
+
- not trained yet TTS-data or the second one
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
|
|
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
| 27 |
+
This is final finetuned version of Wav2vec2 on the sample data of audio from 11 Indian Languages codemixed with English language.
|
| 28 |
+
It has only been yet finetuned on one dataset that is sample dataset.
|
| 29 |
|
| 30 |
## Intended uses & limitations
|
| 31 |
|
| 32 |
+
Not giving yet good accuracy on other datasets like TTS and sample dataset. Needs to be trained on more dataset.
|
| 33 |
|
| 34 |
## Training and evaluation data
|
| 35 |
|