Hugging Face's logo

ramesh070
/
mms-malayalam-binary

Audio Classification
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
ramesh070 commited on
Commit
04bdca2
·
verified ·
1 Parent(s): 1db2126

Model save

Browse files
Files changed (2) hide show
  1. README.md +86 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: facebook/mms-300m
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: mms-malayalam-binary
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # mms-malayalam-binary
19
+
20
+ This model is a fine-tuned version of [facebook/mms-300m](https://huggingface.co/facebook/mms-300m) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1517
23
+ - Accuracy: 0.9773
24
+ - F1: 0.9787
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 3e-05
44
+ - train_batch_size: 8
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 32
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 20
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
59
+ | 0.6653 | 1.0 | 23 | 0.6820 | 0.7955 | 0.7805 |
60
+ | 0.5764 | 2.0 | 46 | 0.4134 | 0.9205 | 0.9213 |
61
+ | 0.3843 | 3.0 | 69 | 0.1825 | 0.9659 | 0.9677 |
62
+ | 0.2285 | 4.0 | 92 | 0.1695 | 0.9659 | 0.9677 |
63
+ | 0.1649 | 5.0 | 115 | 0.1108 | 0.9773 | 0.9787 |
64
+ | 0.1394 | 6.0 | 138 | 0.1390 | 0.9659 | 0.9677 |
65
+ | 0.1141 | 7.0 | 161 | 0.1329 | 0.9659 | 0.9677 |
66
+ | 0.0798 | 8.0 | 184 | 0.1043 | 0.9773 | 0.9787 |
67
+ | 0.0743 | 9.0 | 207 | 0.2201 | 0.9432 | 0.9451 |
68
+ | 0.0846 | 10.0 | 230 | 0.2657 | 0.9205 | 0.9213 |
69
+ | 0.0701 | 11.0 | 253 | 0.1470 | 0.9659 | 0.9677 |
70
+ | 0.082 | 12.0 | 276 | 0.1956 | 0.9545 | 0.9565 |
71
+ | 0.0145 | 13.0 | 299 | 0.1265 | 0.9773 | 0.9787 |
72
+ | 0.0191 | 14.0 | 322 | 0.1345 | 0.9773 | 0.9787 |
73
+ | 0.0355 | 15.0 | 345 | 0.1394 | 0.9773 | 0.9787 |
74
+ | 0.038 | 16.0 | 368 | 0.1432 | 0.9773 | 0.9787 |
75
+ | 0.0437 | 17.0 | 391 | 0.1467 | 0.9773 | 0.9787 |
76
+ | 0.0374 | 18.0 | 414 | 0.1494 | 0.9773 | 0.9787 |
77
+ | 0.0125 | 19.0 | 437 | 0.1511 | 0.9773 | 0.9787 |
78
+ | 0.0575 | 20.0 | 460 | 0.1517 | 0.9773 | 0.9787 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.53.3
84
+ - Pytorch 2.9.1+cu128
85
+ - Datasets 4.4.1
86
+ - Tokenizers 0.21.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dfc0ffb806301dcecfeec2ceb91a207824040d347715a49821d1c66e257c19e
3
  size 1262859296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d951e48ad5b1b5086c38592aac2a30944ab439e87396c8657969525bbb46ef
3
  size 1262859296