PereLluis13
commited on
Commit
•
89fc6f3
1
Parent(s):
efc51f9
Update README.md
Browse files
README.md
CHANGED
@@ -26,10 +26,10 @@ model-index:
|
|
26 |
metrics:
|
27 |
- name: Test WER
|
28 |
type: wer
|
29 |
-
value: 0.
|
30 |
- name: Test CER
|
31 |
type: cer
|
32 |
-
value: 0.
|
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.
|
44 |
- name: Test CER
|
45 |
type: cer
|
46 |
-
value: 0.
|
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.
|
58 |
- name: Test CER
|
59 |
type: cer
|
60 |
-
value: 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
|