Hugging Face's logo

speech-seq2seq
/
wav2vec2-2-bert-large-no-adapter

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
Generated from Trainer
Model card Files
xet
Metrics Community
1
Sanchit Gandhi commited on
Commit
7a3eaca
·
1 Parent(s): c93a6f5

update model card README.md

Browse files
Files changed (2) hide show
  1. README.md +13 -13
  2. runs/Feb21_09-27-04_sanchit--v100/events.out.tfevents.1645435652.sanchit--v100.80427.0 +2 -2
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on the librispeech_asr dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 6.9553
19
- - Wer: 2.0097
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0003
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 6.8818 | 0.28 | 500 | 7.0258 | 1.0 |
55
- | 6.7558 | 0.56 | 1000 | 6.9731 | 1.0 |
56
- | 6.587 | 0.84 | 1500 | 6.9588 | 2.0097 |
57
- | 6.881 | 1.12 | 2000 | 6.9579 | 2.0097 |
58
- | 6.9616 | 1.4 | 2500 | 6.9553 | 2.0097 |
59
- | 6.8572 | 1.68 | 3000 | 6.9488 | 2.0097 |
60
- | 6.8827 | 1.96 | 3500 | 6.9496 | 2.0097 |
61
- | 6.8313 | 2.24 | 4000 | 6.9496 | 2.0097 |
62
- | 6.9634 | 2.52 | 4500 | 6.9445 | 2.0097 |
63
- | 6.7935 | 2.8 | 5000 | 6.9553 | 2.0097 |
64
 
65
 
66
  ### Framework versions
 
15
 
16
  This model was trained from scratch on the librispeech_asr dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.9280
19
+ - Wer: 0.9561
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 3e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 5.3825 | 0.28 | 500 | 5.5398 | 0.9602 |
55
+ | 4.6164 | 0.56 | 1000 | 4.8871 | 0.9781 |
56
+ | 4.5587 | 0.84 | 1500 | 4.6683 | 1.0010 |
57
+ | 4.3428 | 1.12 | 2000 | 4.4745 | 1.6443 |
58
+ | 4.2545 | 1.4 | 2500 | 4.2854 | 1.3727 |
59
+ | 4.0861 | 1.68 | 3000 | 4.1451 | 1.3667 |
60
+ | 4.0882 | 1.96 | 3500 | 4.0432 | 1.2540 |
61
+ | 3.5985 | 2.24 | 4000 | 4.0155 | 1.0706 |
62
+ | 3.7731 | 2.52 | 4500 | 3.9633 | 1.0627 |
63
+ | 3.6984 | 2.8 | 5000 | 3.9280 | 0.9561 |
64
 
65
 
66
  ### Framework versions
runs/Feb21_09-27-04_sanchit--v100/events.out.tfevents.1645435652.sanchit--v100.80427.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b2e40f77abbb2da4cfe34ff8397d9bfaee50abafb22b6da75f6d32c95cec4a6
3
- size 816940
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671be3aa42f8164598f0829f12bd3ff966b533e3887e7980e692949565e015b0
3
+ size 824476