Hugging Face's logo

Shawal777
/
nyankole_wav2vec2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Shawal777 commited on
Commit
bc44030
•
1 Parent(s): a7fed3f

End of training

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: nyankole_wav2vec2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # nyankole_wav2vec2
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.8615
21
+ - Wer: 1.0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0003
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 8
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 150
49
+ - num_epochs: 30
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-------:|:----:|:---------------:|:---:|
56
+ | 2.9097 | 0.9976 | 210 | 2.9031 | 1.0 |
57
+ | 2.8649 | 2.0 | 421 | 2.8534 | 1.0 |
58
+ | 2.8545 | 2.9976 | 631 | 2.8537 | 1.0 |
59
+ | 2.8465 | 4.0 | 842 | 2.8554 | 1.0 |
60
+ | 2.8509 | 4.9976 | 1052 | 2.8629 | 1.0 |
61
+ | 2.8491 | 6.0 | 1263 | 2.8828 | 1.0 |
62
+ | 2.8463 | 6.9976 | 1473 | 2.8570 | 1.0 |
63
+ | 2.8477 | 8.0 | 1684 | 2.8675 | 1.0 |
64
+ | 2.8478 | 8.9976 | 1894 | 2.8605 | 1.0 |
65
+ | 2.8411 | 10.0 | 2105 | 2.8593 | 1.0 |
66
+ | 2.8493 | 10.9976 | 2315 | 2.8573 | 1.0 |
67
+ | 2.8478 | 12.0 | 2526 | 2.8564 | 1.0 |
68
+ | 2.8823 | 12.9976 | 2736 | 2.8538 | 1.0 |
69
+ | 2.8413 | 14.0 | 2947 | 2.8534 | 1.0 |
70
+ | 2.8497 | 14.9976 | 3157 | 2.8487 | 1.0 |
71
+ | 2.8439 | 16.0 | 3368 | 2.8642 | 1.0 |
72
+ | 2.8442 | 16.9976 | 3578 | 2.8527 | 1.0 |
73
+ | 2.8425 | 18.0 | 3789 | 2.8611 | 1.0 |
74
+ | 2.841 | 18.9976 | 3999 | 2.8617 | 1.0 |
75
+ | 2.8426 | 20.0 | 4210 | 2.8563 | 1.0 |
76
+ | 2.8454 | 20.9976 | 4420 | 2.8527 | 1.0 |
77
+ | 2.8396 | 22.0 | 4631 | 2.8568 | 1.0 |
78
+ | 2.8449 | 22.9976 | 4841 | 2.8503 | 1.0 |
79
+ | 2.8424 | 24.0 | 5052 | 2.8596 | 1.0 |
80
+ | 2.8438 | 24.9976 | 5262 | 2.8624 | 1.0 |
81
+ | 2.8414 | 26.0 | 5473 | 2.8606 | 1.0 |
82
+ | 2.8387 | 26.9976 | 5683 | 2.8635 | 1.0 |
83
+ | 2.8408 | 28.0 | 5894 | 2.8569 | 1.0 |
84
+ | 2.8729 | 28.9976 | 6104 | 2.8640 | 1.0 |
85
+ | 2.8417 | 29.9287 | 6300 | 2.8615 | 1.0 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.42.4
91
+ - Pytorch 2.1.0+cu118
92
+ - Datasets 2.20.0
93
+ - Tokenizers 0.19.1