PereLluis13 commited on
Commit
89fc6f3
1 Parent(s): efc51f9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -9
README.md CHANGED
@@ -26,10 +26,10 @@ model-index:
26
  metrics:
27
  - name: Test WER
28
  type: wer
29
- value: 0.08108860330598514
30
  - name: Test CER
31
  type: cer
32
- value: 0.027241712812152218
33
  - task:
34
  name: Speech Recognition
35
  type: automatic-speech-recognition
@@ -40,10 +40,10 @@ model-index:
40
  metrics:
41
  - name: Test WER
42
  type: wer
43
- value: 0.06541946111307212
44
  - name: Test CER
45
  type: cer
46
- value: 0.02205785796827398
47
  - task:
48
  name: Speech Recognition
49
  type: automatic-speech-recognition
@@ -54,19 +54,33 @@ model-index:
54
  metrics:
55
  - name: Test WER
56
  type: wer
57
- value: 0.1506717480848443
58
  - name: Test CER
59
  type: cer
60
- value: 0.09562445266717665
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  ---
62
 
63
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
64
  should probably proofread and complete it, then remove this comment. -->
65
 
66
- # wav2vec2-xls-r-300m-ca
67
 
68
  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 - CA dataset.
69
- It achieves the following results on the averaged across datasets test set:
70
  - Loss: 0.2758
71
  - Wer: 0.1792
72
 
@@ -125,7 +139,29 @@ The following hyperparameters were used during training:
125
  | 1.1407 | 5.33 | 10000 | 0.2768 | 0.1798 |
126
  | 1.1401 | 5.59 | 10500 | 0.2780 | 0.1816 |
127
  | 1.1333 | 5.86 | 11000 | 0.2748 | 0.1750 |
128
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
129
 
130
  ### Framework versions
131
 
 
26
  metrics:
27
  - name: Test WER
28
  type: wer
29
+ value: 0.08040489847285752
30
  - name: Test CER
31
  type: cer
32
+ value: 0.02745409135817121
33
  - task:
34
  name: Speech Recognition
35
  type: automatic-speech-recognition
 
40
  metrics:
41
  - name: Test WER
42
  type: wer
43
+ value: 0.05763423147821312
44
  - name: Test CER
45
  type: cer
46
+ value: 0.019116372518121653
47
  - task:
48
  name: Speech Recognition
49
  type: automatic-speech-recognition
 
54
  metrics:
55
  - name: Test WER
56
  type: wer
57
+ value: 0.13993147784578666
58
  - name: Test CER
59
  type: cer
60
+ value: 0.08941471299857044
61
+ - task:
62
+ name: Speech Recognition
63
+ type: automatic-speech-recognition
64
+ dataset:
65
+ name: Robust Speech Event - Catalan Dev Data
66
+ type: speech-recognition-community-v2/dev_data
67
+ args: ca
68
+ metrics:
69
+ - name: Test WER
70
+ type: wer
71
+ value: 0.26797799000695716
72
+ - name: Test CER
73
+ type: cer
74
+ value: 0.15358004827031377
75
  ---
76
 
77
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
78
  should probably proofread and complete it, then remove this comment. -->
79
 
80
+ # wav2vec2-xls-r-300m-ca-lm
81
 
82
  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 - CA dataset.
83
+ It achieves the following results on the averaged across datasets test set (without the LM):
84
  - Loss: 0.2758
85
  - Wer: 0.1792
86
 
 
139
  | 1.1407 | 5.33 | 10000 | 0.2768 | 0.1798 |
140
  | 1.1401 | 5.59 | 10500 | 0.2780 | 0.1816 |
141
  | 1.1333 | 5.86 | 11000 | 0.2748 | 0.1750 |
142
+ | 1.1571 | 6.13 | 11500 | 0.2808 | 0.1708 |
143
+ | 1.1505 | 6.39 | 12000 | 0.2726 | 0.1692 |
144
+ | 1.1519 | 6.66 | 12500 | 0.2749 | 0.1654 |
145
+ | 1.136 | 6.93 | 13000 | 0.2765 | 0.1643 |
146
+ | 1.1326 | 7.19 | 13500 | 0.2706 | 0.1668 |
147
+ | 1.1342 | 7.46 | 14000 | 0.2665 | 0.1638 |
148
+ | 1.1286 | 7.72 | 14500 | 0.2669 | 0.1636 |
149
+ | 1.1243 | 7.99 | 15000 | 0.2619 | 0.1623 |
150
+ | 1.1173 | 8.26 | 15500 | 0.2652 | 0.1604 |
151
+ | 1.1129 | 8.52 | 16000 | 0.2610 | 0.1598 |
152
+ | 1.1091 | 8.79 | 16500 | 0.2608 | 0.1584 |
153
+ | 1.1053 | 9.06 | 17000 | 0.2633 | 0.1664 |
154
+ | 1.1004 | 9.32 | 17500 | 0.2594 | 0.1662 |
155
+ | 1.0995 | 9.59 | 18000 | 0.2623 | 0.1569 |
156
+ | 1.0964 | 9.86 | 18500 | 0.2624 | 0.1597 |
157
+ | 1.09 | 10.12 | 19000 | 0.2577 | 0.1578 |
158
+ | 1.089 | 10.39 | 19500 | 0.2574 | 0.1531 |
159
+ | 1.0864 | 10.66 | 20000 | 0.2556 | 0.1546 |
160
+ | 1.0806 | 10.92 | 20500 | 0.2548 | 0.1583 |
161
+ | 1.0842 | 11.19 | 21000 | 0.2550 | 0.1542 |
162
+ | 1.0805 | 11.45 | 21500 | 0.2561 | 0.1524 |
163
+ | 1.0722 | 11.72 | 22000 | 0.2540 | 0.1566 |
164
+ | 1.0763 | 11.99 | 22500 | 0.2549 | 0.1572 |
165
 
166
  ### Framework versions
167