DrishtiSharma
commited on
Commit
•
85eb616
1
Parent(s):
5686eac
Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ language:
|
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- automatic-speech-recognition
|
7 |
-
- mozilla-foundation/
|
8 |
- generated_from_trainer
|
9 |
- bas
|
10 |
- robust-speech-event
|
@@ -12,7 +12,7 @@ tags:
|
|
12 |
datasets:
|
13 |
- common_voice
|
14 |
model-index:
|
15 |
-
- name: wav2vec2-large-xls-r-300m-bas-v1
|
16 |
results:
|
17 |
- task:
|
18 |
name: Automatic Speech Recognition
|
@@ -20,10 +20,14 @@ model-index:
|
|
20 |
dataset:
|
21 |
name: Common Voice 8
|
22 |
type: mozilla-foundation/common_voice_8_0
|
23 |
-
args:
|
24 |
-
|
25 |
-
|
26 |
-
|
|
|
|
|
|
|
|
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,7 +35,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
# wav2vec2-large-xls-r-300m-bas-v1
|
33 |
|
34 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the
|
35 |
It achieves the following results on the evaluation set:
|
36 |
- Loss: 0.5997
|
37 |
- Wer: 0.3870
|
|
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- automatic-speech-recognition
|
7 |
+
- mozilla-foundation/common_voice_8_0
|
8 |
- generated_from_trainer
|
9 |
- bas
|
10 |
- robust-speech-event
|
|
|
12 |
datasets:
|
13 |
- common_voice
|
14 |
model-index:
|
15 |
+
- name: wav2vec2-large-xls-r-300m-bas-v1
|
16 |
results:
|
17 |
- task:
|
18 |
name: Automatic Speech Recognition
|
|
|
20 |
dataset:
|
21 |
name: Common Voice 8
|
22 |
type: mozilla-foundation/common_voice_8_0
|
23 |
+
args: bas
|
24 |
+
metrics:
|
25 |
+
- name: Test WER
|
26 |
+
type: wer
|
27 |
+
value: 0.35664979291302346
|
28 |
+
- name: Test CER
|
29 |
+
type: cer
|
30 |
+
value: 0.11026576341844711
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# wav2vec2-large-xls-r-300m-bas-v1
|
37 |
|
38 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - BAS dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
- Loss: 0.5997
|
41 |
- Wer: 0.3870
|