Commit
•
57f9bca
1
Parent(s):
c50d054
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,11 +3,18 @@ license: apache-2.0
|
|
| 3 |
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
metrics:
|
| 7 |
- wer
|
| 8 |
model-index:
|
| 9 |
- name: wav2vec2-large-xlsr-300m-hi-kagglex
|
| 10 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -21,18 +28,6 @@ It achieves the following results on the evaluation set:
|
|
| 21 |
- Wer: 0.3285
|
| 22 |
- Cer: 0.0875
|
| 23 |
|
| 24 |
-
## Model description
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Intended uses & limitations
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training and evaluation data
|
| 33 |
-
|
| 34 |
-
More information needed
|
| 35 |
-
|
| 36 |
## Training procedure
|
| 37 |
|
| 38 |
### Training hyperparameters
|
|
@@ -66,3 +61,6 @@ The following hyperparameters were used during training:
|
|
| 66 |
- Pytorch 2.0.0
|
| 67 |
- Datasets 2.1.0
|
| 68 |
- Tokenizers 0.13.3
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
- code
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
- name: wav2vec2-large-xlsr-300m-hi-kagglex
|
| 11 |
results: []
|
| 12 |
+
datasets:
|
| 13 |
+
- SakshiRathi77/ASR_CV15_Hindi_wav_16000
|
| 14 |
+
language:
|
| 15 |
+
- hi
|
| 16 |
+
library_name: transformers
|
| 17 |
+
pipeline_tag: automatic-speech-recognition
|
| 18 |
---
|
| 19 |
|
| 20 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 28 |
- Wer: 0.3285
|
| 29 |
- Cer: 0.0875
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## Training procedure
|
| 32 |
|
| 33 |
### Training hyperparameters
|
|
|
|
| 61 |
- Pytorch 2.0.0
|
| 62 |
- Datasets 2.1.0
|
| 63 |
- Tokenizers 0.13.3
|
| 64 |
+
|
| 65 |
+
### SPACE
|
| 66 |
+
[Automatic Speech Recognization in hindi](https://huggingface.co/spaces/SakshiRathi77/SakshiRathi77-Wishper-Hi-Kagglex)
|