Hugging Face's logo

csikasote
/
mms-1b-all-swagen-combined-m50f50-dnn-42-0.04

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
swagen
mms
Generated from Trainer
Model card Files
xet
Community
csikasote commited on
Commit
fb04220
·
verified ·
1 Parent(s): 76d8493

Model save

Browse files
Files changed (2) hide show
  1. README.md +12 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,9 +3,6 @@ library_name: transformers
3
  license: cc-by-nc-4.0
4
  base_model: facebook/mms-1b-all
5
  tags:
6
- - automatic-speech-recognition
7
- - swagen
8
- - mms
9
  - generated_from_trainer
10
  model-index:
11
  - name: mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
@@ -17,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
19
 
20
- This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the SWAGEN - DEB dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4168
23
- - Cer: 0.0823
24
 
25
  ## Model description
26
 
@@ -53,20 +50,18 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Cer |
57
- |:-------------:|:-------:|:----:|:---------------:|:------:|
58
- | 2.3933 | 1.9723 | 250 | 2.6004 | 0.8549 |
59
- | 0.3234 | 3.9407 | 500 | 0.6526 | 0.1453 |
60
- | 0.9916 | 5.9091 | 750 | 0.4272 | 0.0755 |
61
- | 0.2123 | 7.8775 | 1000 | 0.4168 | 0.0822 |
62
- | 0.2050 | 9.8458 | 1250 | 0.3905 | 0.0780 |
63
- | 0.2602 | 11.8142 | 1500 | 0.4448 | 0.0977 |
64
- | 1.7064 | 13.7826 | 1750 | 0.4683 | 0.1055 |
65
 
66
 
67
  ### Framework versions
68
 
69
- - Transformers 4.53.0.dev0
70
  - Pytorch 2.6.0+cu124
71
  - Datasets 3.6.0
72
- - Tokenizers 0.21.0
 
3
  license: cc-by-nc-4.0
4
  base_model: facebook/mms-1b-all
5
  tags:
 
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
 
14
 
15
  # mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
16
 
17
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6629
20
+ - Cer: 0.1582
21
 
22
  ## Model description
23
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 2.2783 | 1.9723 | 250 | 2.5115 | 0.8079 |
56
+ | 0.3398 | 3.9407 | 500 | 0.5567 | 0.1128 |
57
+ | 1.5759 | 5.9091 | 750 | 0.8367 | 0.2037 |
58
+ | 0.2443 | 7.8775 | 1000 | 0.5941 | 0.1357 |
59
+ | 0.3935 | 9.8458 | 1250 | 0.6629 | 0.1582 |
 
 
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.53.0
65
  - Pytorch 2.6.0+cu124
66
  - Datasets 3.6.0
67
+ - Tokenizers 0.21.4
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f835bac7145ebb84c44a8daff47b8b328cc3c7ab5ca8d23cf2c2e1f0c0d1f89c
3
  size 3878630084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5636857aa5d55f4ca5eb94df03af71887073b7ac818872588265bfc96f41f86a
3
  size 3878630084