Hugging Face's logo

asr-africa
/
bambara-mms-10-hours-oza75bambara-asr-hf

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
dmusingu commited on
Commit
8d0e18d
·
verified ·
1 Parent(s): adbe0d6

asr-africa/bambara-mms-10-hours-oza75bambara-asr-hf

Browse files
Files changed (2) hide show
  1. README.md +72 -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-10-hours-oza75bambara-asr-hf
9
  results: []
@@ -16,6 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
16
  # bambara-mms-10-hours-oza75bambara-asr-hf
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 +51,72 @@ 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-10-hours-oza75bambara-asr-hf
11
  results: []
 
18
  # bambara-mms-10-hours-oza75bambara-asr-hf
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: 2.1148
23
+ - Wer: 0.5199
24
+ - Cer: 0.2465
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
+ | 1.5938 | 0.8313 | 500 | 1.2774 | 0.8294 | 0.3861 |
59
+ | 1.5142 | 1.6625 | 1000 | 1.2540 | 0.7729 | 0.3702 |
60
+ | 1.3973 | 2.4938 | 1500 | 1.2161 | 0.7125 | 0.3521 |
61
+ | 1.326 | 3.3250 | 2000 | 1.1719 | 0.7260 | 0.3426 |
62
+ | 1.2698 | 4.1563 | 2500 | 1.1710 | 0.6738 | 0.3350 |
63
+ | 1.218 | 4.9875 | 3000 | 1.0692 | 0.6507 | 0.3147 |
64
+ | 1.1672 | 5.8188 | 3500 | 1.0691 | 0.6408 | 0.3071 |
65
+ | 1.1307 | 6.6500 | 4000 | 1.0518 | 0.6405 | 0.3035 |
66
+ | 1.079 | 7.4813 | 4500 | 1.1091 | 0.6304 | 0.2972 |
67
+ | 1.0474 | 8.3126 | 5000 | 1.0662 | 0.6240 | 0.2994 |
68
+ | 1.0169 | 9.1438 | 5500 | 1.0669 | 0.6173 | 0.2937 |
69
+ | 0.9753 | 9.9751 | 6000 | 1.0039 | 0.6329 | 0.3027 |
70
+ | 0.9303 | 10.8063 | 6500 | 0.9909 | 0.6101 | 0.2863 |
71
+ | 0.8867 | 11.6376 | 7000 | 1.0058 | 0.5929 | 0.2888 |
72
+ | 0.8537 | 12.4688 | 7500 | 1.0321 | 0.6015 | 0.2859 |
73
+ | 0.8268 | 13.3001 | 8000 | 1.0427 | 0.5960 | 0.2808 |
74
+ | 0.7908 | 14.1313 | 8500 | 1.0816 | 0.5847 | 0.2791 |
75
+ | 0.7625 | 14.9626 | 9000 | 1.0817 | 0.5839 | 0.2748 |
76
+ | 0.7254 | 15.7938 | 9500 | 1.1185 | 0.5764 | 0.2768 |
77
+ | 0.6817 | 16.6251 | 10000 | 1.1043 | 0.5658 | 0.2749 |
78
+ | 0.6602 | 17.4564 | 10500 | 1.1736 | 0.5640 | 0.2708 |
79
+ | 0.6244 | 18.2876 | 11000 | 1.1894 | 0.5725 | 0.2721 |
80
+ | 0.6073 | 19.1189 | 11500 | 1.2478 | 0.5647 | 0.2737 |
81
+ | 0.5752 | 19.9501 | 12000 | 1.1698 | 0.5671 | 0.2770 |
82
+ | 0.5457 | 20.7814 | 12500 | 1.1864 | 0.5587 | 0.2697 |
83
+ | 0.5231 | 21.6126 | 13000 | 1.1907 | 0.5592 | 0.2693 |
84
+ | 0.5018 | 22.4439 | 13500 | 1.1874 | 0.5675 | 0.2707 |
85
+ | 0.4756 | 23.2751 | 14000 | 1.2167 | 0.5626 | 0.2664 |
86
+ | 0.458 | 24.1064 | 14500 | 1.2149 | 0.5592 | 0.2712 |
87
+ | 0.4301 | 24.9377 | 15000 | 1.3165 | 0.5499 | 0.2660 |
88
+ | 0.4165 | 25.7689 | 15500 | 1.2436 | 0.5689 | 0.2713 |
89
+ | 0.3897 | 26.6002 | 16000 | 1.3646 | 0.5470 | 0.2624 |
90
+ | 0.3743 | 27.4314 | 16500 | 1.4319 | 0.5477 | 0.2623 |
91
+ | 0.355 | 28.2627 | 17000 | 1.4645 | 0.5580 | 0.2683 |
92
+ | 0.3414 | 29.0939 | 17500 | 1.5373 | 0.5508 | 0.2590 |
93
+ | 0.3251 | 29.9252 | 18000 | 1.4997 | 0.5473 | 0.2648 |
94
+ | 0.3049 | 30.7564 | 18500 | 1.5231 | 0.5494 | 0.2617 |
95
+ | 0.2924 | 31.5877 | 19000 | 1.6212 | 0.5490 | 0.2610 |
96
+ | 0.2807 | 32.4190 | 19500 | 1.5959 | 0.5571 | 0.2661 |
97
+ | 0.2669 | 33.2502 | 20000 | 1.6300 | 0.5478 | 0.2628 |
98
+ | 0.2575 | 34.0815 | 20500 | 1.7042 | 0.5447 | 0.2616 |
99
+ | 0.2426 | 34.9127 | 21000 | 1.6750 | 0.5430 | 0.2607 |
100
+ | 0.2301 | 35.7440 | 21500 | 1.7449 | 0.5421 | 0.2596 |
101
+ | 0.2202 | 36.5752 | 22000 | 1.6587 | 0.5418 | 0.2584 |
102
+ | 0.213 | 37.4065 | 22500 | 1.7982 | 0.5361 | 0.2546 |
103
+ | 0.2092 | 38.2377 | 23000 | 1.7748 | 0.5271 | 0.2537 |
104
+ | 0.1956 | 39.0690 | 23500 | 1.8427 | 0.5310 | 0.2562 |
105
+ | 0.1869 | 39.9002 | 24000 | 1.7940 | 0.5275 | 0.2541 |
106
+ | 0.1799 | 40.7315 | 24500 | 1.7794 | 0.5275 | 0.2520 |
107
+ | 0.1727 | 41.5628 | 25000 | 1.9008 | 0.5374 | 0.2540 |
108
+ | 0.1681 | 42.3940 | 25500 | 1.9119 | 0.5297 | 0.2522 |
109
+ | 0.1596 | 43.2253 | 26000 | 1.9836 | 0.5258 | 0.2472 |
110
+ | 0.1569 | 44.0565 | 26500 | 1.9823 | 0.5195 | 0.2472 |
111
+ | 0.1516 | 44.8878 | 27000 | 1.9638 | 0.5179 | 0.2483 |
112
+ | 0.1482 | 45.7190 | 27500 | 2.0763 | 0.5146 | 0.2468 |
113
+ | 0.1379 | 46.5503 | 28000 | 2.0760 | 0.5234 | 0.2483 |
114
+ | 0.1407 | 47.3815 | 28500 | 2.0269 | 0.5220 | 0.2482 |
115
+ | 0.1331 | 48.2128 | 29000 | 2.0818 | 0.5221 | 0.2481 |
116
+ | 0.1328 | 49.0441 | 29500 | 2.0947 | 0.5205 | 0.2467 |
117
+ | 0.1308 | 49.8753 | 30000 | 2.1148 | 0.5199 | 0.2465 |
118
+
119
+
120
  ### Framework versions
121
 
122
  - Transformers 4.45.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1976206743c1c825831abc6cd1b44ceab3345b3d1202919bddd834a94d689602
3
  size 3859521176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469287b3d0270354b64d3246c644b24d333c80a0db5ddf684013d170aec26d18
3
  size 3859521176