Hugging Face's logo

asr-africa
/
bambara_mms_20_hour_jeli_asr_dataset

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
dmusingu commited on
Commit
707ea0d
•
1 Parent(s): dcca708

asr-africa/bambara_mms_20_hour_jeli_asr_dataset

Browse files
Files changed (2) hide show
  1. README.md +126 -0
  2. model.safetensors +1 -1
README.md CHANGED
@@ -4,6 +4,8 @@ license: cc-by-nc-4.0
4
  base_model: facebook/mms-1b-all
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: bambara_mms_20_hour_jeli_asr_dataset
9
  results: []
@@ -16,6 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
16
  # bambara_mms_20_hour_jeli_asr_dataset
17
 
18
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
 
 
 
 
19
 
20
  ## Model description
21
 
@@ -45,6 +51,126 @@ The following hyperparameters were used during training:
45
  - lr_scheduler_warmup_steps: 500
46
  - num_epochs: 50
47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - Transformers 4.45.1
 
4
  base_model: facebook/mms-1b-all
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: bambara_mms_20_hour_jeli_asr_dataset
11
  results: []
 
18
  # bambara_mms_20_hour_jeli_asr_dataset
19
 
20
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 2.5960
23
+ - Wer: 0.1951
24
+ - Cer: 0.0927
25
 
26
  ## Model description
27
 
 
51
  - lr_scheduler_warmup_steps: 500
52
  - num_epochs: 50
53
 
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
58
+ | 2.3781 | 0.4365 | 500 | 1.7790 | 0.9007 | 0.4152 |
59
+ | 1.5271 | 0.8730 | 1000 | 1.4809 | 0.7424 | 0.3462 |
60
+ | 1.4216 | 1.3095 | 1500 | 1.4134 | 0.8316 | 0.4020 |
61
+ | 1.3995 | 1.7460 | 2000 | 1.3669 | 0.7422 | 0.3379 |
62
+ | 1.3521 | 2.1825 | 2500 | 1.2531 | 0.6969 | 0.3176 |
63
+ | 1.3161 | 2.6189 | 3000 | 1.3363 | 0.6643 | 0.3061 |
64
+ | 1.2759 | 3.0554 | 3500 | 1.2953 | 0.6607 | 0.3018 |
65
+ | 1.2604 | 3.4919 | 4000 | 1.2630 | 0.6280 | 0.2889 |
66
+ | 1.2424 | 3.9284 | 4500 | 1.4642 | 0.6308 | 0.2847 |
67
+ | 1.1639 | 4.3649 | 5000 | 1.3593 | 0.6216 | 0.2797 |
68
+ | 1.2122 | 4.8014 | 5500 | 1.2043 | 0.5966 | 0.2716 |
69
+ | 1.1504 | 5.2379 | 6000 | 1.1364 | 0.5892 | 0.2688 |
70
+ | 1.156 | 5.6744 | 6500 | 1.1405 | 0.6049 | 0.2726 |
71
+ | 1.1371 | 6.1109 | 7000 | 1.1854 | 0.5817 | 0.2633 |
72
+ | 1.0981 | 6.5474 | 7500 | 1.1306 | 0.5876 | 0.2625 |
73
+ | 1.1021 | 6.9838 | 8000 | 1.1026 | 0.5910 | 0.2659 |
74
+ | 1.0295 | 7.4203 | 8500 | 1.2506 | 0.5671 | 0.2600 |
75
+ | 1.0702 | 7.8568 | 9000 | 1.1672 | 0.5521 | 0.2529 |
76
+ | 1.0277 | 8.2933 | 9500 | 1.0966 | 0.5616 | 0.2544 |
77
+ | 1.0023 | 8.7298 | 10000 | 1.1389 | 0.5353 | 0.2403 |
78
+ | 0.9945 | 9.1663 | 10500 | 1.3434 | 0.5302 | 0.2420 |
79
+ | 0.9533 | 9.6028 | 11000 | 1.1546 | 0.5391 | 0.2517 |
80
+ | 0.9675 | 10.0393 | 11500 | 1.1966 | 0.5355 | 0.2451 |
81
+ | 0.9061 | 10.4758 | 12000 | 1.1808 | 0.5116 | 0.2310 |
82
+ | 0.9243 | 10.9123 | 12500 | 1.1189 | 0.5095 | 0.2290 |
83
+ | 0.8834 | 11.3488 | 13000 | 1.2189 | 0.4979 | 0.2226 |
84
+ | 0.8819 | 11.7852 | 13500 | 1.2035 | 0.4910 | 0.2158 |
85
+ | 0.8522 | 12.2217 | 14000 | 1.1385 | 0.4961 | 0.2173 |
86
+ | 0.8417 | 12.6582 | 14500 | 1.1060 | 0.4787 | 0.2110 |
87
+ | 0.8352 | 13.0947 | 15000 | 1.1295 | 0.4957 | 0.2237 |
88
+ | 0.7857 | 13.5312 | 15500 | 1.0946 | 0.4814 | 0.2142 |
89
+ | 0.7963 | 13.9677 | 16000 | 1.0891 | 0.4844 | 0.2240 |
90
+ | 0.762 | 14.4042 | 16500 | 1.0606 | 0.4832 | 0.2177 |
91
+ | 0.7594 | 14.8407 | 17000 | 1.0415 | 0.4529 | 0.1992 |
92
+ | 0.7368 | 15.2772 | 17500 | 1.0882 | 0.4399 | 0.1930 |
93
+ | 0.7158 | 15.7137 | 18000 | 1.0872 | 0.4521 | 0.1972 |
94
+ | 0.7102 | 16.1502 | 18500 | 1.0949 | 0.4259 | 0.1842 |
95
+ | 0.6789 | 16.5866 | 19000 | 1.1207 | 0.4138 | 0.1821 |
96
+ | 0.6898 | 17.0231 | 19500 | 1.1287 | 0.4105 | 0.1792 |
97
+ | 0.6463 | 17.4596 | 20000 | 1.2131 | 0.4103 | 0.1793 |
98
+ | 0.6525 | 17.8961 | 20500 | 1.1986 | 0.4001 | 0.1733 |
99
+ | 0.6116 | 18.3326 | 21000 | 1.2255 | 0.4058 | 0.1778 |
100
+ | 0.6138 | 18.7691 | 21500 | 1.2027 | 0.3946 | 0.1762 |
101
+ | 0.6033 | 19.2056 | 22000 | 1.1681 | 0.3870 | 0.1686 |
102
+ | 0.5816 | 19.6421 | 22500 | 1.1464 | 0.3822 | 0.1662 |
103
+ | 0.5826 | 20.0786 | 23000 | 1.1767 | 0.3817 | 0.1651 |
104
+ | 0.5504 | 20.5151 | 23500 | 1.2805 | 0.3796 | 0.1664 |
105
+ | 0.5656 | 20.9515 | 24000 | 1.1895 | 0.3634 | 0.1581 |
106
+ | 0.5204 | 21.3880 | 24500 | 1.2111 | 0.3569 | 0.1531 |
107
+ | 0.5186 | 21.8245 | 25000 | 1.2840 | 0.3526 | 0.1541 |
108
+ | 0.5074 | 22.2610 | 25500 | 1.2123 | 0.3564 | 0.1558 |
109
+ | 0.4966 | 22.6975 | 26000 | 1.1740 | 0.3467 | 0.1511 |
110
+ | 0.4886 | 23.1340 | 26500 | 1.3208 | 0.3351 | 0.1459 |
111
+ | 0.4628 | 23.5705 | 27000 | 1.3905 | 0.3277 | 0.1439 |
112
+ | 0.4743 | 24.0070 | 27500 | 1.3396 | 0.3378 | 0.1469 |
113
+ | 0.4408 | 24.4435 | 28000 | 1.3767 | 0.3164 | 0.1384 |
114
+ | 0.4457 | 24.8800 | 28500 | 1.2607 | 0.3231 | 0.1364 |
115
+ | 0.4242 | 25.3165 | 29000 | 1.2562 | 0.3181 | 0.1383 |
116
+ | 0.4279 | 25.7529 | 29500 | 1.2523 | 0.3198 | 0.1379 |
117
+ | 0.4116 | 26.1894 | 30000 | 1.3625 | 0.3086 | 0.1332 |
118
+ | 0.3963 | 26.6259 | 30500 | 1.2143 | 0.3132 | 0.1346 |
119
+ | 0.3945 | 27.0624 | 31000 | 1.2973 | 0.2993 | 0.1320 |
120
+ | 0.3733 | 27.4989 | 31500 | 1.3542 | 0.2955 | 0.1296 |
121
+ | 0.3816 | 27.9354 | 32000 | 1.3804 | 0.2946 | 0.1307 |
122
+ | 0.3487 | 28.3719 | 32500 | 1.4206 | 0.2841 | 0.1233 |
123
+ | 0.3521 | 28.8084 | 33000 | 1.4294 | 0.2819 | 0.1236 |
124
+ | 0.3351 | 29.2449 | 33500 | 1.5658 | 0.2797 | 0.1218 |
125
+ | 0.3285 | 29.6814 | 34000 | 1.5103 | 0.2803 | 0.1235 |
126
+ | 0.3253 | 30.1179 | 34500 | 1.4957 | 0.2704 | 0.1209 |
127
+ | 0.308 | 30.5543 | 35000 | 1.6964 | 0.2648 | 0.1173 |
128
+ | 0.3184 | 30.9908 | 35500 | 1.4796 | 0.2609 | 0.1153 |
129
+ | 0.2941 | 31.4273 | 36000 | 1.5527 | 0.2597 | 0.1169 |
130
+ | 0.2897 | 31.8638 | 36500 | 1.5907 | 0.2574 | 0.1150 |
131
+ | 0.2883 | 32.3003 | 37000 | 1.5718 | 0.2536 | 0.1132 |
132
+ | 0.2792 | 32.7368 | 37500 | 1.5505 | 0.2527 | 0.1134 |
133
+ | 0.2773 | 33.1733 | 38000 | 1.6607 | 0.2480 | 0.1102 |
134
+ | 0.2579 | 33.6098 | 38500 | 1.8962 | 0.2461 | 0.1108 |
135
+ | 0.2658 | 34.0463 | 39000 | 1.9136 | 0.2426 | 0.1116 |
136
+ | 0.2539 | 34.4828 | 39500 | 1.9131 | 0.2440 | 0.1113 |
137
+ | 0.2501 | 34.9192 | 40000 | 1.7290 | 0.2368 | 0.1083 |
138
+ | 0.2358 | 35.3557 | 40500 | 1.9586 | 0.2309 | 0.1059 |
139
+ | 0.2395 | 35.7922 | 41000 | 1.7617 | 0.2295 | 0.1040 |
140
+ | 0.2267 | 36.2287 | 41500 | 1.8779 | 0.2264 | 0.1021 |
141
+ | 0.2239 | 36.6652 | 42000 | 1.8696 | 0.2248 | 0.1019 |
142
+ | 0.2183 | 37.1017 | 42500 | 1.8445 | 0.2229 | 0.1026 |
143
+ | 0.2149 | 37.5382 | 43000 | 1.9865 | 0.2265 | 0.1041 |
144
+ | 0.2125 | 37.9747 | 43500 | 1.8998 | 0.2252 | 0.1039 |
145
+ | 0.2001 | 38.4112 | 44000 | 2.0591 | 0.2214 | 0.1010 |
146
+ | 0.204 | 38.8477 | 44500 | 1.9436 | 0.2145 | 0.1004 |
147
+ | 0.1967 | 39.2842 | 45000 | 2.0536 | 0.2148 | 0.0994 |
148
+ | 0.1902 | 39.7206 | 45500 | 2.0584 | 0.2161 | 0.1000 |
149
+ | 0.1862 | 40.1571 | 46000 | 2.0744 | 0.2146 | 0.1004 |
150
+ | 0.182 | 40.5936 | 46500 | 2.0731 | 0.2108 | 0.0982 |
151
+ | 0.1876 | 41.0301 | 47000 | 2.0895 | 0.2096 | 0.0978 |
152
+ | 0.1744 | 41.4666 | 47500 | 2.2355 | 0.2038 | 0.0956 |
153
+ | 0.178 | 41.9031 | 48000 | 2.1099 | 0.2099 | 0.0969 |
154
+ | 0.1677 | 42.3396 | 48500 | 2.2260 | 0.2043 | 0.0959 |
155
+ | 0.1688 | 42.7761 | 49000 | 2.2102 | 0.2046 | 0.0949 |
156
+ | 0.1676 | 43.2126 | 49500 | 2.2165 | 0.2047 | 0.0965 |
157
+ | 0.1589 | 43.6491 | 50000 | 2.2741 | 0.2016 | 0.0937 |
158
+ | 0.1613 | 44.0856 | 50500 | 2.2069 | 0.2021 | 0.0947 |
159
+ | 0.1529 | 44.5220 | 51000 | 2.3035 | 0.2018 | 0.0958 |
160
+ | 0.1513 | 44.9585 | 51500 | 2.4750 | 0.2007 | 0.0957 |
161
+ | 0.1515 | 45.3950 | 52000 | 2.5079 | 0.2011 | 0.0956 |
162
+ | 0.1463 | 45.8315 | 52500 | 2.5247 | 0.1994 | 0.0944 |
163
+ | 0.1433 | 46.2680 | 53000 | 2.5564 | 0.1968 | 0.0934 |
164
+ | 0.143 | 46.7045 | 53500 | 2.5230 | 0.1970 | 0.0933 |
165
+ | 0.1399 | 47.1410 | 54000 | 2.5532 | 0.1954 | 0.0927 |
166
+ | 0.1377 | 47.5775 | 54500 | 2.4811 | 0.1985 | 0.0933 |
167
+ | 0.1358 | 48.0140 | 55000 | 2.6065 | 0.1980 | 0.0934 |
168
+ | 0.1373 | 48.4505 | 55500 | 2.5808 | 0.1951 | 0.0926 |
169
+ | 0.1327 | 48.8869 | 56000 | 2.5458 | 0.1954 | 0.0930 |
170
+ | 0.1329 | 49.3234 | 56500 | 2.5948 | 0.1942 | 0.0927 |
171
+ | 0.1361 | 49.7599 | 57000 | 2.5960 | 0.1951 | 0.0927 |
172
+
173
+
174
  ### Framework versions
175
 
176
  - Transformers 4.45.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac5ae8393ce2888194291cdd99660ee6766dd773d165f3f943e621d3ca33ed35
3
  size 3858957536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd21942056b8fc2a9d677c0fd3209405592e508554e8e7e46003214ee13644ac
3
  size 3858957536