Hugging Face's logo

asr-africa
/
bambara_mms_10_hour_mixed_dataset

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
dmusingu commited on
Commit
fe1b386
•
1 Parent(s): b792693

asr-africa/bambara_mms_10_hour_mixed_dataset

Browse files
Files changed (1) hide show
  1. README.md +70 -0
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_hour_mixed_dataset
9
  results: []
@@ -16,6 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
16
  # bambara_mms_10_hour_mixed_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 +51,70 @@ 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_hour_mixed_dataset
11
  results: []
 
18
  # bambara_mms_10_hour_mixed_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: 2.2512
23
+ - Wer: 0.52
24
+ - Cer: 0.3632
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
+ | 1.9455 | 0.8482 | 500 | 1.5056 | 0.8112 | 0.4290 |
59
+ | 1.5004 | 1.6964 | 1000 | 1.3041 | 0.7323 | 0.3374 |
60
+ | 1.3813 | 2.5445 | 1500 | 1.2313 | 0.7115 | 0.3728 |
61
+ | 1.3102 | 3.3927 | 2000 | 1.1950 | 0.7120 | 0.4489 |
62
+ | 1.2181 | 4.2409 | 2500 | 1.1980 | 0.6981 | 0.4080 |
63
+ | 1.174 | 5.0891 | 3000 | 1.1699 | 0.7216 | 0.3960 |
64
+ | 1.1191 | 5.9372 | 3500 | 1.1130 | 0.7440 | 0.4183 |
65
+ | 1.0556 | 6.7854 | 4000 | 1.0874 | 0.6244 | 0.3241 |
66
+ | 1.0105 | 7.6336 | 4500 | 1.0767 | 0.6353 | 0.3932 |
67
+ | 0.9775 | 8.4818 | 5000 | 1.1265 | 0.6319 | 0.3856 |
68
+ | 0.9283 | 9.3299 | 5500 | 1.1483 | 0.6483 | 0.4394 |
69
+ | 0.8955 | 10.1781 | 6000 | 1.0845 | 0.6544 | 0.4310 |
70
+ | 0.852 | 11.0263 | 6500 | 1.0088 | 0.5970 | 0.3317 |
71
+ | 0.7987 | 11.8745 | 7000 | 1.0797 | 0.6010 | 0.3611 |
72
+ | 0.7569 | 12.7226 | 7500 | 1.0715 | 0.6100 | 0.3884 |
73
+ | 0.7299 | 13.5708 | 8000 | 1.1275 | 0.6071 | 0.3978 |
74
+ | 0.6995 | 14.4190 | 8500 | 1.1741 | 0.6209 | 0.4731 |
75
+ | 0.6671 | 15.2672 | 9000 | 1.0855 | 0.5953 | 0.3887 |
76
+ | 0.6431 | 16.1154 | 9500 | 1.1793 | 0.5662 | 0.3377 |
77
+ | 0.612 | 16.9635 | 10000 | 1.1662 | 0.5778 | 0.3876 |
78
+ | 0.5784 | 17.8117 | 10500 | 1.1753 | 0.5764 | 0.3820 |
79
+ | 0.5501 | 18.6599 | 11000 | 1.2029 | 0.5832 | 0.3877 |
80
+ | 0.5286 | 19.5081 | 11500 | 1.3072 | 0.6082 | 0.4344 |
81
+ | 0.5066 | 20.3562 | 12000 | 1.1977 | 0.5755 | 0.3815 |
82
+ | 0.4812 | 21.2044 | 12500 | 1.2332 | 0.5624 | 0.3667 |
83
+ | 0.4609 | 22.0526 | 13000 | 1.3325 | 0.5465 | 0.3521 |
84
+ | 0.4338 | 22.9008 | 13500 | 1.3214 | 0.5512 | 0.3628 |
85
+ | 0.4244 | 23.7489 | 14000 | 1.4046 | 0.5612 | 0.3858 |
86
+ | 0.3963 | 24.5971 | 14500 | 1.4522 | 0.5704 | 0.3985 |
87
+ | 0.3844 | 25.4453 | 15000 | 1.3522 | 0.5706 | 0.3945 |
88
+ | 0.3665 | 26.2935 | 15500 | 1.3853 | 0.5391 | 0.3524 |
89
+ | 0.3494 | 27.1416 | 16000 | 1.5375 | 0.5476 | 0.3784 |
90
+ | 0.3338 | 27.9898 | 16500 | 1.4892 | 0.5563 | 0.3732 |
91
+ | 0.3172 | 28.8380 | 17000 | 1.5445 | 0.5500 | 0.3761 |
92
+ | 0.308 | 29.6862 | 17500 | 1.6170 | 0.5530 | 0.3821 |
93
+ | 0.2871 | 30.5344 | 18000 | 1.6431 | 0.5499 | 0.3889 |
94
+ | 0.2724 | 31.3825 | 18500 | 1.6469 | 0.5362 | 0.3614 |
95
+ | 0.2653 | 32.2307 | 19000 | 1.6854 | 0.5428 | 0.3648 |
96
+ | 0.2505 | 33.0789 | 19500 | 1.7214 | 0.5413 | 0.3654 |
97
+ | 0.2405 | 33.9271 | 20000 | 1.7085 | 0.5550 | 0.3809 |
98
+ | 0.2304 | 34.7752 | 20500 | 1.7357 | 0.5467 | 0.3772 |
99
+ | 0.2259 | 35.6234 | 21000 | 1.7828 | 0.5465 | 0.3799 |
100
+ | 0.2111 | 36.4716 | 21500 | 1.8705 | 0.5350 | 0.3678 |
101
+ | 0.2014 | 37.3198 | 22000 | 1.8758 | 0.5361 | 0.3682 |
102
+ | 0.2016 | 38.1679 | 22500 | 1.9686 | 0.5344 | 0.3842 |
103
+ | 0.1884 | 39.0161 | 23000 | 1.9711 | 0.5288 | 0.3742 |
104
+ | 0.1842 | 39.8643 | 23500 | 1.9821 | 0.5337 | 0.3827 |
105
+ | 0.1745 | 40.7125 | 24000 | 1.9664 | 0.5262 | 0.3730 |
106
+ | 0.1665 | 41.5606 | 24500 | 2.0731 | 0.5327 | 0.3733 |
107
+ | 0.1639 | 42.4088 | 25000 | 2.1357 | 0.5286 | 0.3694 |
108
+ | 0.1536 | 43.2570 | 25500 | 2.0855 | 0.5290 | 0.3640 |
109
+ | 0.1532 | 44.1052 | 26000 | 2.1890 | 0.5238 | 0.3635 |
110
+ | 0.1443 | 44.9534 | 26500 | 2.1638 | 0.5296 | 0.3666 |
111
+ | 0.1428 | 45.8015 | 27000 | 2.1495 | 0.5232 | 0.3624 |
112
+ | 0.1377 | 46.6497 | 27500 | 2.2047 | 0.5234 | 0.3580 |
113
+ | 0.1348 | 47.4979 | 28000 | 2.2385 | 0.5215 | 0.3651 |
114
+ | 0.1285 | 48.3461 | 28500 | 2.2492 | 0.5203 | 0.3650 |
115
+ | 0.1303 | 49.1942 | 29000 | 2.2512 | 0.52 | 0.3632 |
116
+
117
+
118
  ### Framework versions
119
 
120
  - Transformers 4.45.1