DrishtiSharma commited on
Commit
e978c00
1 Parent(s): c241a89

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -9
README.md CHANGED
@@ -28,6 +28,35 @@ model-index:
28
  - name: Test CER
29
  type: cer
30
  value: 0.10205125354383235
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,19 +69,15 @@ It achieves the following results on the evaluation set:
40
  - Loss: 0.5197
41
  - Wer: 0.4689
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
 
 
28
  - name: Test CER
29
  type: cer
30
  value: 0.10205125354383235
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: bg
38
+ metrics:
39
+ - name: Test WER
40
+ type: wer
41
+ value: 0.4709579127785184
42
+ - name: Test CER
43
+ type: cer
44
+ value: 0.10205125354383235
45
+ - task:
46
+ name: Automatic Speech Recognition
47
+ type: automatic-speech-recognition
48
+ dataset:
49
+ name: Robust Speech Event - Dev Data
50
+ type: speech-recognition-community-v2/dev_data
51
+ args: bg
52
+ metrics:
53
+ - name: Test WER
54
+ type: wer
55
+ value: 0.7053128872366791
56
+ - name: Test CER
57
+ type: cer
58
+ value: 0.210804311998487
59
+
60
  ---
61
 
62
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
69
  - Loss: 0.5197
70
  - Wer: 0.4689
71
 
72
+ ### Evaluation Commands
 
 
 
 
73
 
74
+ 1. To evaluate on mozilla-foundation/common_voice_8_0 with test split
75
 
76
+ python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-bg-v1 --dataset mozilla-foundation/common_voice_8_0 --config bg --split test --log_outputs
77
 
78
+ 2. To evaluate on speech-recognition-community-v2/dev_data
79
 
80
+ python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-bg-v1 --dataset speech-recognition-community-v2/dev_data --config bg --split validation --chunk_length_s 10 --stride_length_s 1
81
 
82
  ### Training hyperparameters
83