patrickvonplaten commited on
Commit
814d86e
1 Parent(s): 69e53ad

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - automatic-speech-recognition
4
+ - librispeech_asr
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: wav2vec2-2-bart-base
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # wav2vec2-2-bart-base
15
+
16
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) and [bart-base](https://huggingface.co/facebook/bart-base) on the librispeech_asr - clean dataset.
17
+
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.405
20
+ - Wer: 0.0728
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: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - total_train_batch_size: 64
46
+ - total_eval_batch_size: 64
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 400
50
+ - num_epochs: 5
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ See Training Metrics Tab.
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.15.0.dev0
61
+ - Pytorch 1.9.0+cu111
62
+ - Datasets 1.16.2.dev0
63
+ - Tokenizers 0.10.3