Hugging Face's logo

csikasote
/
mms-zeroshot-300m-bem

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
BembaSpeech
mms
Generated from Trainer
Inference Endpoints
Model card Files Community
csikasote commited on
Commit
e254d0e
·
verified ·
1 Parent(s): 4013eac

Model save

Browse files
Files changed (2) hide show
  1. README.md +118 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: mms-meta/mms-zeroshot-300m
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: mms-zeroshot-300m-bem
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # mms-zeroshot-300m-bem
18
+
19
+ This model is a fine-tuned version of [mms-meta/mms-zeroshot-300m](https://huggingface.co/mms-meta/mms-zeroshot-300m) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1788
22
+ - Wer: 0.3588
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0003
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 10.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
55
+ | 4.6629 | 0.1778 | 500 | 0.3540 | 0.5421 |
56
+ | 0.6579 | 0.3556 | 1000 | 0.2588 | 0.4883 |
57
+ | 0.591 | 0.5334 | 1500 | 0.2552 | 0.4720 |
58
+ | 0.5467 | 0.7112 | 2000 | 0.2370 | 0.4542 |
59
+ | 0.5405 | 0.8890 | 2500 | 0.2376 | 0.4556 |
60
+ | 0.5027 | 1.0669 | 3000 | 0.2234 | 0.4307 |
61
+ | 0.5001 | 1.2447 | 3500 | 0.2176 | 0.4213 |
62
+ | 0.4962 | 1.4225 | 4000 | 0.2199 | 0.4205 |
63
+ | 0.486 | 1.6003 | 4500 | 0.2145 | 0.4167 |
64
+ | 0.47 | 1.7781 | 5000 | 0.2159 | 0.4169 |
65
+ | 0.4557 | 1.9559 | 5500 | 0.2099 | 0.4135 |
66
+ | 0.4514 | 2.1337 | 6000 | 0.2091 | 0.4100 |
67
+ | 0.4539 | 2.3115 | 6500 | 0.2038 | 0.4016 |
68
+ | 0.439 | 2.4893 | 7000 | 0.2041 | 0.4025 |
69
+ | 0.4378 | 2.6671 | 7500 | 0.2002 | 0.3916 |
70
+ | 0.4347 | 2.8450 | 8000 | 0.1961 | 0.3911 |
71
+ | 0.4278 | 3.0228 | 8500 | 0.1995 | 0.3923 |
72
+ | 0.4117 | 3.2006 | 9000 | 0.1959 | 0.3892 |
73
+ | 0.4149 | 3.3784 | 9500 | 0.1926 | 0.3859 |
74
+ | 0.4148 | 3.5562 | 10000 | 0.1958 | 0.3804 |
75
+ | 0.4009 | 3.7340 | 10500 | 0.1930 | 0.3790 |
76
+ | 0.4174 | 3.9118 | 11000 | 0.1955 | 0.3823 |
77
+ | 0.4012 | 4.0896 | 11500 | 0.1950 | 0.3812 |
78
+ | 0.3974 | 4.2674 | 12000 | 0.1934 | 0.3773 |
79
+ | 0.3943 | 4.4452 | 12500 | 0.1845 | 0.3720 |
80
+ | 0.4071 | 4.6230 | 13000 | 0.1920 | 0.3839 |
81
+ | 0.3968 | 4.8009 | 13500 | 0.1867 | 0.3743 |
82
+ | 0.3795 | 4.9787 | 14000 | 0.1872 | 0.3713 |
83
+ | 0.3856 | 5.1565 | 14500 | 0.1869 | 0.3737 |
84
+ | 0.3706 | 5.3343 | 15000 | 0.1903 | 0.3766 |
85
+ | 0.3784 | 5.5121 | 15500 | 0.1861 | 0.3683 |
86
+ | 0.3777 | 5.6899 | 16000 | 0.1866 | 0.3713 |
87
+ | 0.3861 | 5.8677 | 16500 | 0.1812 | 0.3637 |
88
+ | 0.3711 | 6.0455 | 17000 | 0.1842 | 0.3667 |
89
+ | 0.374 | 6.2233 | 17500 | 0.1815 | 0.3618 |
90
+ | 0.3539 | 6.4011 | 18000 | 0.1815 | 0.3647 |
91
+ | 0.3625 | 6.5789 | 18500 | 0.1785 | 0.3589 |
92
+ | 0.3599 | 6.7568 | 19000 | 0.1795 | 0.3621 |
93
+ | 0.3654 | 6.9346 | 19500 | 0.1822 | 0.3624 |
94
+ | 0.3693 | 7.1124 | 20000 | 0.1792 | 0.3612 |
95
+ | 0.3519 | 7.2902 | 20500 | 0.1800 | 0.3675 |
96
+ | 0.3553 | 7.4680 | 21000 | 0.1808 | 0.3640 |
97
+ | 0.3451 | 7.6458 | 21500 | 0.1808 | 0.3620 |
98
+ | 0.3558 | 7.8236 | 22000 | 0.1794 | 0.3610 |
99
+ | 0.3595 | 8.0014 | 22500 | 0.1772 | 0.3576 |
100
+ | 0.3404 | 8.1792 | 23000 | 0.1788 | 0.3581 |
101
+ | 0.3593 | 8.3570 | 23500 | 0.1782 | 0.3580 |
102
+ | 0.3471 | 8.5349 | 24000 | 0.1797 | 0.3606 |
103
+ | 0.3497 | 8.7127 | 24500 | 0.1778 | 0.3588 |
104
+ | 0.3398 | 8.8905 | 25000 | 0.1775 | 0.3583 |
105
+ | 0.3444 | 9.0683 | 25500 | 0.1796 | 0.3586 |
106
+ | 0.3366 | 9.2461 | 26000 | 0.1785 | 0.3574 |
107
+ | 0.3434 | 9.4239 | 26500 | 0.1781 | 0.3592 |
108
+ | 0.3426 | 9.6017 | 27000 | 0.1786 | 0.3593 |
109
+ | 0.3496 | 9.7795 | 27500 | 0.1787 | 0.3590 |
110
+ | 0.334 | 9.9573 | 28000 | 0.1788 | 0.3588 |
111
+
112
+
113
+ ### Framework versions
114
+
115
+ - Transformers 4.45.0.dev0
116
+ - Pytorch 2.4.0+cu121
117
+ - Datasets 2.21.0
118
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48282dff39c1cf259b157034457c94ffa679d34a2729eff2bf603f8ad8b4f798
3
  size 1265394748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:416a69b23b935e985d5623df5b5082f1d8b8b43f4a72cf6e71ab18731cf2daea
3
  size 1265394748