Automatic correction of README.md metadata. Contact [email protected] for any question
Browse files
README.md
CHANGED
@@ -9,11 +9,11 @@ tags:
|
|
9 |
- automatic-speech-recognition
|
10 |
- speech
|
11 |
- xlsr-fine-tuning-week
|
12 |
-
license:
|
13 |
model-index:
|
14 |
- name: XLSR Wav2Vec2 Bengali by Tanmoy Sarkar
|
15 |
results:
|
16 |
-
- task:
|
17 |
name: Speech Recognition
|
18 |
type: automatic-speech-recognition
|
19 |
dataset:
|
@@ -21,9 +21,9 @@ model-index:
|
|
21 |
type: OpenSLR
|
22 |
args: ben
|
23 |
metrics:
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
---
|
28 |
# Wav2Vec2-Large-XLSR-Bengali
|
29 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) Bengali using the [Bengali ASR training data set containing ~196K utterances](https://www.openslr.org/53/).
|
|
|
9 |
- automatic-speech-recognition
|
10 |
- speech
|
11 |
- xlsr-fine-tuning-week
|
12 |
+
license: cc-by-sa-4.0
|
13 |
model-index:
|
14 |
- name: XLSR Wav2Vec2 Bengali by Tanmoy Sarkar
|
15 |
results:
|
16 |
+
- task:
|
17 |
name: Speech Recognition
|
18 |
type: automatic-speech-recognition
|
19 |
dataset:
|
|
|
21 |
type: OpenSLR
|
22 |
args: ben
|
23 |
metrics:
|
24 |
+
- name: Test WER
|
25 |
+
type: wer
|
26 |
+
value: 88.58
|
27 |
---
|
28 |
# Wav2Vec2-Large-XLSR-Bengali
|
29 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) Bengali using the [Bengali ASR training data set containing ~196K utterances](https://www.openslr.org/53/).
|