patrickvonplaten commited on
Commit
e73289c
1 Parent(s): e85edf8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +73 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - automatic-speech-recognition
5
+ - multilingual_librispeech
6
+ - generated_from_trainer
7
+ datasets:
8
+ - multilingual_librispeech
9
+ model-index:
10
+ - name: wav2vec2-100m-mls-german-ft-2
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
+ # wav2vec2-100m-mls-german-ft-2
18
+
19
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-100m](https://huggingface.co/facebook/wav2vec2-xls-r-100m) on the MULTILINGUAL_LIBRISPEECH - GERMAN dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.9304
22
+ - Wer: 1.0
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: 0.0005
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 8
47
+ - total_train_batch_size: 64
48
+ - total_eval_batch_size: 64
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 1000
52
+ - num_epochs: 100.0
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
59
+ | 2.9545 | 14.29 | 500 | 2.9354 | 1.0 |
60
+ | 2.9537 | 28.57 | 1000 | 2.9359 | 1.0 |
61
+ | 2.9602 | 42.86 | 1500 | 2.9302 | 1.0 |
62
+ | 2.9586 | 57.14 | 2000 | 2.9298 | 1.0 |
63
+ | 2.9331 | 71.43 | 2500 | 2.9314 | 1.0 |
64
+ | 2.9321 | 85.71 | 3000 | 2.9304 | 1.0 |
65
+ | 2.9652 | 100.0 | 3500 | 2.9304 | 1.0 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.13.0.dev0
71
+ - Pytorch 1.9.0+cu111
72
+ - Datasets 1.15.2.dev0
73
+ - Tokenizers 0.10.3