Hugging Face's logo

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

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
bemgen
mms
Generated from Trainer
Inference Endpoints
Model card Files Community
csikasote commited on
Commit
3f35920
•
1 Parent(s): 3c604a1

Model save

Browse files
Files changed (2) hide show
  1. README.md +104 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.2478
22
+ - Wer: 0.3899
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: 4
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
+ | 6.8762 | 0.0516 | 100 | 0.9801 | 0.9386 |
56
+ | 0.5788 | 0.1031 | 200 | 0.3466 | 0.5014 |
57
+ | 0.4891 | 0.1547 | 300 | 0.3220 | 0.4820 |
58
+ | 0.4386 | 0.2063 | 400 | 0.3071 | 0.4802 |
59
+ | 0.4272 | 0.2579 | 500 | 0.3056 | 0.4988 |
60
+ | 0.3982 | 0.3094 | 600 | 0.2981 | 0.4626 |
61
+ | 0.425 | 0.3610 | 700 | 0.2977 | 0.4631 |
62
+ | 0.4036 | 0.4126 | 800 | 0.2897 | 0.4438 |
63
+ | 0.3903 | 0.4642 | 900 | 0.2878 | 0.4627 |
64
+ | 0.3758 | 0.5157 | 1000 | 0.2926 | 0.4523 |
65
+ | 0.3861 | 0.5673 | 1100 | 0.2807 | 0.4410 |
66
+ | 0.3763 | 0.6189 | 1200 | 0.2790 | 0.4331 |
67
+ | 0.3984 | 0.6704 | 1300 | 0.2803 | 0.4312 |
68
+ | 0.373 | 0.7220 | 1400 | 0.2802 | 0.4246 |
69
+ | 0.3848 | 0.7736 | 1500 | 0.2759 | 0.4752 |
70
+ | 0.4235 | 0.8252 | 1600 | 0.2738 | 0.4268 |
71
+ | 0.3704 | 0.8767 | 1700 | 0.2688 | 0.4219 |
72
+ | 0.3911 | 0.9283 | 1800 | 0.2653 | 0.4201 |
73
+ | 0.3954 | 0.9799 | 1900 | 0.2697 | 0.4482 |
74
+ | 0.352 | 1.0315 | 2000 | 0.2654 | 0.4154 |
75
+ | 0.3808 | 1.0830 | 2100 | 0.2631 | 0.4051 |
76
+ | 0.3681 | 1.1346 | 2200 | 0.2610 | 0.4219 |
77
+ | 0.3355 | 1.1862 | 2300 | 0.2608 | 0.4098 |
78
+ | 0.342 | 1.2378 | 2400 | 0.2602 | 0.4082 |
79
+ | 0.347 | 1.2893 | 2500 | 0.2628 | 0.4055 |
80
+ | 0.3409 | 1.3409 | 2600 | 0.2588 | 0.4129 |
81
+ | 0.3423 | 1.3925 | 2700 | 0.2617 | 0.4192 |
82
+ | 0.3341 | 1.4440 | 2800 | 0.2578 | 0.4055 |
83
+ | 0.3425 | 1.4956 | 2900 | 0.2580 | 0.3988 |
84
+ | 0.337 | 1.5472 | 3000 | 0.2568 | 0.4071 |
85
+ | 0.3412 | 1.5988 | 3100 | 0.2552 | 0.3993 |
86
+ | 0.3837 | 1.6503 | 3200 | 0.2622 | 0.4084 |
87
+ | 0.3372 | 1.7019 | 3300 | 0.2548 | 0.3991 |
88
+ | 0.3394 | 1.7535 | 3400 | 0.2535 | 0.4061 |
89
+ | 0.3542 | 1.8051 | 3500 | 0.2512 | 0.3927 |
90
+ | 0.3368 | 1.8566 | 3600 | 0.2580 | 0.4004 |
91
+ | 0.3807 | 1.9082 | 3700 | 0.2490 | 0.3975 |
92
+ | 0.3454 | 1.9598 | 3800 | 0.2514 | 0.4002 |
93
+ | 0.3456 | 2.0113 | 3900 | 0.2457 | 0.3931 |
94
+ | 0.3202 | 2.0629 | 4000 | 0.2466 | 0.3916 |
95
+ | 0.3233 | 2.1145 | 4100 | 0.2495 | 0.3975 |
96
+ | 0.3052 | 2.1661 | 4200 | 0.2478 | 0.3899 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.47.1
102
+ - Pytorch 2.5.1+cu124
103
+ - Datasets 3.2.0
104
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46162a54d764ccf90734d9a7cd609d33e06811cc279f6ad4314ce8aa881b237a
3
  size 3858890924
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b08075f2242876ed31a2d70374017b8eb2fd2f946d2ed3a3d7b69e169f6fd1
3
  size 3858890924