Hugging Face's logo

pinot
/
wav2vec2-xls-r-300m-ja-phoneme_cv_14_3

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
pinot commited on
Commit
5bb2c60
·
1 Parent(s): b1bdc59

First model version

Browse files
Files changed (3) hide show
  1. README.md +6 -8
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.10693675936260656
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4916
36
- - Wer: 0.1069
37
 
38
  ## Model description
39
 
@@ -61,16 +61,14 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - num_epochs: 2
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 5.385 | 0.44 | 400 | 2.8758 | 1.0 |
71
- | 1.7331 | 0.88 | 800 | 0.7472 | 0.1574 |
72
- | 0.7526 | 1.32 | 1200 | 0.5581 | 0.1175 |
73
- | 0.6261 | 1.76 | 1600 | 0.4916 | 0.1069 |
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.1460970338882424
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7558
36
+ - Wer: 0.1461
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 1
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 5.2909 | 0.44 | 400 | 2.8888 | 1.0 |
71
+ | 1.7369 | 0.88 | 800 | 0.7558 | 0.1461 |
 
 
72
 
73
 
74
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cd85275bc69a9dbda740ff59b1f6507e1baf25bdc3f49e7faa0c5854c164801
3
  size 1262123245
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33646ed222248ed040f7d02f413799b60076e4b2d08951a7bb3408df011be1c
3
  size 1262123245
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b43cbd98431dbabfe67ed0e1f94fafab1c259bb49afd268c925b16a95b640ea
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d87c3667815277ff2f17c78278ea8da7fee68ee4bde8b4dce17fa0fcbd853525
3
  size 4091