DrishtiSharma commited on
Commit
01a794c
1 Parent(s): 6a254c9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -15
README.md CHANGED
@@ -28,6 +28,20 @@ model-index:
28
  - name: Test CER
29
  type: cer
30
  value: 0.10630270750110964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,19 +54,17 @@ It achieves the following results on the evaluation set:
40
  - Loss: 0.5620
41
  - Wer: 0.5651
42
 
43
- ## Model description
44
 
45
- More information needed
46
 
47
- ## Intended uses & limitations
48
 
49
- More information needed
50
 
51
- ## Training and evaluation data
52
 
53
- More information needed
54
 
55
- ## Training procedure
56
 
57
  ### Training hyperparameters
58
 
@@ -88,11 +100,3 @@ The following hyperparameters were used during training:
88
  - Pytorch 1.10.1+cu102
89
  - Datasets 1.17.1.dev0
90
  - Tokenizers 0.11.0
91
-
92
- ### Evaluation Script
93
-
94
- Evaluation script for evaluating the performance of the fine-tuned model on Mozilla-foundation/common_voice_7_0 with split test
95
-
96
- !python eval.py \
97
- --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-ab-v16 \
98
- --dataset mozilla-foundation/common_voice_7_0 --config ab --split test --log_outputs
 
28
  - name: Test CER
29
  type: cer
30
  value: 0.10630270750110964
31
+ - task:
32
+ name: Automatic Speech Recognition
33
+ type: automatic-speech-recognition
34
+ dataset:
35
+ name: Robust Speech Event - Dev Data
36
+ type: speech-recognition-community-v2/dev_data
37
+ args: ab
38
+ metrics:
39
+ - name: Test WER
40
+ type: wer
41
+ value: NA
42
+ - name: Test CER
43
+ type: cer
44
+ value: NA
45
  ---
46
 
47
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
54
  - Loss: 0.5620
55
  - Wer: 0.5651
56
 
57
+ ### Evaluation Commands
58
 
59
+ 1. To evaluate on mozilla-foundation/common_voice_8_0 with test split
60
 
61
+ python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-ab-CV7 --dataset mozilla-foundation/common_voice_7_0 --config ab --split test --log_outputs
62
 
63
+ 2. To evaluate on speech-recognition-community-v2/dev_data
64
 
65
+ NA
66
 
 
67
 
 
68
 
69
  ### Training hyperparameters
70
 
 
100
  - Pytorch 1.10.1+cu102
101
  - Datasets 1.17.1.dev0
102
  - Tokenizers 0.11.0