Hugging Face's logo

csikasote
/
mms-1b-bemgen-combined-model

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
genbed
mms
Generated from Trainer
Inference Endpoints
Model card Files Community
csikasote commited on
Commit
07d3820
•
1 Parent(s): 213f108

Model save

Browse files
Files changed (2) hide show
  1. README.md +87 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: facebook/mms-1b-all
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: mms-1b-bemgen-combined-model
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-1b-bemgen-combined-model
18
+
19
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2591
22
+ - Wer: 0.4135
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 100
48
+ - num_epochs: 30.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 6.7553 | 0.0516 | 100 | 0.8774 | 0.8476 |
56
+ | 0.5648 | 0.1031 | 200 | 0.3408 | 0.5032 |
57
+ | 0.4827 | 0.1547 | 300 | 0.3261 | 0.4930 |
58
+ | 0.4321 | 0.2063 | 400 | 0.3036 | 0.4854 |
59
+ | 0.4168 | 0.2579 | 500 | 0.2989 | 0.4783 |
60
+ | 0.3965 | 0.3094 | 600 | 0.2907 | 0.4513 |
61
+ | 0.4199 | 0.3610 | 700 | 0.2926 | 0.4718 |
62
+ | 0.3975 | 0.4126 | 800 | 0.2886 | 0.4459 |
63
+ | 0.3839 | 0.4642 | 900 | 0.2908 | 0.4722 |
64
+ | 0.3673 | 0.5157 | 1000 | 0.2836 | 0.4445 |
65
+ | 0.3777 | 0.5673 | 1100 | 0.2784 | 0.4365 |
66
+ | 0.3764 | 0.6189 | 1200 | 0.2791 | 0.4278 |
67
+ | 0.3918 | 0.6704 | 1300 | 0.2757 | 0.4251 |
68
+ | 0.3669 | 0.7220 | 1400 | 0.2721 | 0.4182 |
69
+ | 0.377 | 0.7736 | 1500 | 0.2728 | 0.4757 |
70
+ | 0.4174 | 0.8252 | 1600 | 0.2684 | 0.4242 |
71
+ | 0.3641 | 0.8767 | 1700 | 0.2649 | 0.4195 |
72
+ | 0.3882 | 0.9283 | 1800 | 0.2647 | 0.4125 |
73
+ | 0.3861 | 0.9799 | 1900 | 0.2668 | 0.4425 |
74
+ | 0.3647 | 1.0315 | 2000 | 0.2675 | 0.4246 |
75
+ | 0.3467 | 1.0830 | 2100 | 0.2629 | 0.4098 |
76
+ | 0.3579 | 1.1346 | 2200 | 0.2587 | 0.4186 |
77
+ | 0.3544 | 1.1862 | 2300 | 0.2609 | 0.4127 |
78
+ | 0.35 | 1.2378 | 2400 | 0.2592 | 0.4062 |
79
+ | 0.3519 | 1.2893 | 2500 | 0.2591 | 0.4135 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.48.0.dev0
85
+ - Pytorch 2.5.1+cu124
86
+ - Datasets 3.2.0
87
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cef43cc7a4de1e8e21607bc1889c0676b7f8752d76b73c891604a90dbd0ce8ef
3
  size 3858890924
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704246731042f485568c7787c0c2392aedbe6069feeac5ef217bb7105b57323b
3
  size 3858890924