Hugging Face's logo

csikasote
/
mms-1b-all-bem-natbed-combined

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
genbed
mms
Generated from Trainer
Inference Endpoints
Model card Files Community
csikasote commited on
Commit
b404a37
•
1 Parent(s): 9c08933

Model save

Browse files
Files changed (2) hide show
  1. README.md +106 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-all-bem-natbed-combined
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-all-bem-natbed-combined
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: 0.5698
22
+ - Wer: 0.4758
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: 8
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: 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
+ | 8.2239 | 0.1252 | 100 | 1.3301 | 0.8960 |
56
+ | 0.8992 | 0.2503 | 200 | 0.7774 | 0.6657 |
57
+ | 0.8263 | 0.3755 | 300 | 0.7550 | 0.5891 |
58
+ | 0.7846 | 0.5006 | 400 | 0.6995 | 0.5665 |
59
+ | 0.9046 | 0.6258 | 500 | 0.6796 | 0.5546 |
60
+ | 0.7688 | 0.7509 | 600 | 0.6881 | 0.5436 |
61
+ | 0.7139 | 0.8761 | 700 | 0.6999 | 0.5557 |
62
+ | 0.7922 | 1.0013 | 800 | 0.6811 | 0.5421 |
63
+ | 0.7929 | 1.1264 | 900 | 0.6760 | 0.5434 |
64
+ | 0.7508 | 1.2516 | 1000 | 0.6555 | 0.5660 |
65
+ | 0.7534 | 1.3767 | 1100 | 0.6411 | 0.5372 |
66
+ | 0.7316 | 1.5019 | 1200 | 0.6420 | 0.5320 |
67
+ | 0.7147 | 1.6270 | 1300 | 0.6726 | 0.5294 |
68
+ | 0.6734 | 1.7522 | 1400 | 0.6308 | 0.5253 |
69
+ | 0.7084 | 1.8773 | 1500 | 0.6205 | 0.5439 |
70
+ | 0.6714 | 2.0025 | 1600 | 0.6119 | 0.5231 |
71
+ | 0.6888 | 2.1277 | 1700 | 0.6350 | 0.5167 |
72
+ | 0.6871 | 2.2528 | 1800 | 0.6183 | 0.5118 |
73
+ | 0.6882 | 2.3780 | 1900 | 0.5974 | 0.5333 |
74
+ | 0.6769 | 2.5031 | 2000 | 0.5995 | 0.5301 |
75
+ | 0.6801 | 2.6283 | 2100 | 0.5880 | 0.5378 |
76
+ | 0.6695 | 2.7534 | 2200 | 0.5973 | 0.5051 |
77
+ | 0.6557 | 2.8786 | 2300 | 0.6027 | 0.5056 |
78
+ | 0.6525 | 3.0038 | 2400 | 0.5946 | 0.4996 |
79
+ | 0.6829 | 3.1289 | 2500 | 0.5882 | 0.4998 |
80
+ | 0.6627 | 3.2541 | 2600 | 0.6010 | 0.4985 |
81
+ | 0.6146 | 3.3792 | 2700 | 0.5770 | 0.5009 |
82
+ | 0.6205 | 3.5044 | 2800 | 0.5739 | 0.5021 |
83
+ | 0.7025 | 3.6295 | 2900 | 0.5806 | 0.5224 |
84
+ | 0.6379 | 3.7547 | 3000 | 0.6210 | 0.5064 |
85
+ | 0.6104 | 3.8798 | 3100 | 0.5702 | 0.5034 |
86
+ | 0.6607 | 4.0050 | 3200 | 0.5756 | 0.4891 |
87
+ | 0.6776 | 4.1302 | 3300 | 0.5679 | 0.4886 |
88
+ | 0.6343 | 4.2553 | 3400 | 0.5598 | 0.4899 |
89
+ | 0.5818 | 4.3805 | 3500 | 0.5807 | 0.4964 |
90
+ | 0.6085 | 4.5056 | 3600 | 0.5932 | 0.4915 |
91
+ | 0.6648 | 4.6308 | 3700 | 0.5580 | 0.4860 |
92
+ | 0.6359 | 4.7559 | 3800 | 0.5565 | 0.4959 |
93
+ | 0.6139 | 4.8811 | 3900 | 0.5605 | 0.4886 |
94
+ | 0.5995 | 5.0063 | 4000 | 0.5720 | 0.4803 |
95
+ | 0.6349 | 5.1314 | 4100 | 0.5506 | 0.5012 |
96
+ | 0.6134 | 5.2566 | 4200 | 0.5603 | 0.4784 |
97
+ | 0.5989 | 5.3817 | 4300 | 0.5714 | 0.4844 |
98
+ | 0.6083 | 5.5069 | 4400 | 0.5698 | 0.4758 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.46.0.dev0
104
+ - Pytorch 2.4.1+cu121
105
+ - Datasets 3.0.1
106
+ - Tokenizers 0.20.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55496b3990fbb8963e68983bcec44a91c5cf43c483dcf6a2af6c48ac6de5f688
3
  size 3858916544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7bde417033c02c9a89105f6fe499b1f040f723006de0854abb905779ad4ad9
3
  size 3858916544