Hugging Face's logo

Chituyi
/
wav2vec2-large-xlsr-sw-sw300m-tr-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
Chituyi commited on
Commit
197aeb9
•
1 Parent(s): 15274fd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -11
README.md CHANGED
@@ -16,12 +16,12 @@ model-index:
16
  name: common_voice_8_0
17
  type: common_voice_8_0
18
  config: sw
19
- split: test[:200]
20
  args: sw
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 1.0
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_8_0 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 2.7491
35
- - Wer: 1.0
36
 
37
  ## Model description
38
 
@@ -60,16 +60,24 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_steps: 50
63
- - num_epochs: 4
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Wer |
68
- |:-------------:|:-----:|:----:|:---------------:|:---:|
69
- | 6.4756 | 0.8 | 50 | 3.0037 | 1.0 |
70
- | 2.8817 | 1.6 | 100 | 2.8536 | 1.0 |
71
- | 2.8365 | 2.4 | 150 | 2.8080 | 1.0 |
72
- | 2.7919 | 3.2 | 200 | 2.7491 | 1.0 |
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
16
  name: common_voice_8_0
17
  type: common_voice_8_0
18
  config: sw
19
+ split: test[:400]
20
  args: sw
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 0.97
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_8_0 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.4900
35
+ - Wer: 0.97
36
 
37
  ## Model description
38
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_steps: 50
63
+ - num_epochs: 5
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
69
+ | 6.5497 | 0.4 | 50 | 2.9819 | 1.0 |
70
+ | 2.8809 | 0.8 | 100 | 2.8873 | 1.0 |
71
+ | 2.8416 | 1.2 | 150 | 2.8427 | 1.0 |
72
+ | 2.8145 | 1.6 | 200 | 2.8067 | 1.0 |
73
+ | 2.747 | 2.0 | 250 | 2.7092 | 1.0 |
74
+ | 2.1095 | 2.4 | 300 | 1.3472 | 1.0 |
75
+ | 0.9546 | 2.8 | 350 | 0.7708 | 0.9975 |
76
+ | 0.6104 | 3.2 | 400 | 0.6317 | 0.9825 |
77
+ | 0.4941 | 3.6 | 450 | 0.5427 | 0.97 |
78
+ | 0.4345 | 4.0 | 500 | 0.5314 | 0.975 |
79
+ | 0.3327 | 4.4 | 550 | 0.4927 | 0.9625 |
80
+ | 0.3099 | 4.8 | 600 | 0.4900 | 0.97 |
81
 
82
 
83
  ### Framework versions