Hugging Face's logo

Umong
/
wav2vec2-xls-r-300m-bengali

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
Umong commited on
Commit
24846f2
•
1 Parent(s): e46305f

End of training

Browse files
Files changed (2) hide show
  1. README.md +91 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Umong/wav2vec2-xls-r-300m-bengali
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: wav2vec2-xls-r-300m-bengali
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-xls-r-300m-bengali
16
+
17
+ This model is a fine-tuned version of [Umong/wav2vec2-xls-r-300m-bengali](https://huggingface.co/Umong/wav2vec2-xls-r-300m-bengali) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1636
20
+ - Wer: 0.0883
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 32
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: 5
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 5.3076 | 0.16 | 400 | 1.5883 | 0.9394 |
55
+ | 0.8841 | 0.33 | 800 | 0.5188 | 0.5337 |
56
+ | 0.5896 | 0.49 | 1200 | 0.4029 | 0.4340 |
57
+ | 0.4964 | 0.66 | 1600 | 0.3429 | 0.3766 |
58
+ | 0.4553 | 0.82 | 2000 | 0.3196 | 0.3642 |
59
+ | 0.4222 | 0.99 | 2400 | 0.3004 | 0.3436 |
60
+ | 0.3709 | 1.15 | 2800 | 0.2812 | 0.3225 |
61
+ | 0.352 | 1.32 | 3200 | 0.2753 | 0.3124 |
62
+ | 0.3283 | 1.48 | 3600 | 0.2616 | 0.2979 |
63
+ | 0.3235 | 1.65 | 4000 | 0.2573 | 0.2944 |
64
+ | 0.3129 | 1.81 | 4400 | 0.2458 | 0.2809 |
65
+ | 0.306 | 1.98 | 4800 | 0.2344 | 0.2771 |
66
+ | 0.2701 | 2.14 | 5200 | 0.2318 | 0.2661 |
67
+ | 0.2653 | 2.31 | 5600 | 0.2253 | 0.2629 |
68
+ | 0.2626 | 2.47 | 6000 | 0.2186 | 0.2542 |
69
+ | 0.2541 | 2.63 | 6400 | 0.2074 | 0.2474 |
70
+ | 0.2235 | 2.8 | 6800 | 0.2102 | 0.2442 |
71
+ | 0.2185 | 2.96 | 7200 | 0.2019 | 0.2327 |
72
+ | 0.2061 | 3.13 | 7600 | 0.1994 | 0.2308 |
73
+ | 0.2011 | 3.29 | 8000 | 0.1942 | 0.2260 |
74
+ | 0.1986 | 3.46 | 8400 | 0.1867 | 0.2187 |
75
+ | 0.197 | 3.62 | 8800 | 0.1825 | 0.2177 |
76
+ | 0.1931 | 3.79 | 9200 | 0.1856 | 0.2153 |
77
+ | 0.1879 | 3.95 | 9600 | 0.1777 | 0.2088 |
78
+ | 0.1599 | 4.12 | 10000 | 0.1781 | 0.0968 |
79
+ | 0.153 | 4.28 | 10400 | 0.1738 | 0.0944 |
80
+ | 0.1475 | 4.45 | 10800 | 0.1713 | 0.0905 |
81
+ | 0.1448 | 4.61 | 11200 | 0.1683 | 0.0907 |
82
+ | 0.1445 | 4.78 | 11600 | 0.1649 | 0.0897 |
83
+ | 0.1423 | 4.94 | 12000 | 0.1636 | 0.0883 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.33.0
89
+ - Pytorch 2.0.0
90
+ - Datasets 2.14.5
91
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24dad9124df1463e19d3d05088062661cb2937016c721a1f875f9d2c16c81086
3
  size 1262172461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee0f15d4482dec9f7073887434bb523fdd0768dae7726e8e385b54ae0907c58
3
  size 1262172461