Hugging Face's logo

makhataei
/
Whisper-Small-Common-Voice

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Persian
whisper
fa-asr
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
makhataei commited on
Commit
3accacc
·
1 Parent(s): 0b24eb8

End of training

Browse files
Files changed (3) hide show
  1. README.md +33 -33
  2. model.safetensors +1 -1
  3. runs/Jan05_01-51-40_Software-AI/events.out.tfevents.1704406903.Software-AI.4154976.0 +2 -2
README.md CHANGED
@@ -22,8 +22,8 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [makhataei/Whisper-Small-Common-Voice](https://huggingface.co/makhataei/Whisper-Small-Common-Voice) on the Common Voice 16.0 dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.7811
26
- - Wer: 43.9230
27
 
28
  ## Model description
29
 
@@ -42,7 +42,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 1e-06
46
  - train_batch_size: 10
47
  - eval_batch_size: 10
48
  - seed: 42
@@ -57,36 +57,36 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer |
59
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
60
- | 0.0014 | 0.16 | 100 | 0.7112 | 43.9740 |
61
- | 0.0048 | 0.31 | 200 | 0.7077 | 42.5968 |
62
- | 0.0048 | 0.47 | 300 | 0.7099 | 42.8982 |
63
- | 0.0032 | 0.62 | 400 | 0.7116 | 43.4802 |
64
- | 0.0041 | 0.78 | 500 | 0.7156 | 43.6935 |
65
- | 0.0025 | 0.93 | 600 | 0.7184 | 43.5660 |
66
- | 0.0012 | 1.09 | 700 | 0.7212 | 44.5421 |
67
- | 0.0005 | 1.25 | 800 | 0.7338 | 43.8164 |
68
- | 0.0014 | 1.4 | 900 | 0.7409 | 44.0529 |
69
- | 0.0009 | 1.56 | 1000 | 0.7414 | 44.3010 |
70
- | 0.001 | 1.71 | 1100 | 0.7408 | 45.0475 |
71
- | 0.0006 | 1.87 | 1200 | 0.7447 | 44.6812 |
72
- | 0.0005 | 2.03 | 1300 | 0.7493 | 43.4268 |
73
- | 0.0005 | 2.18 | 1400 | 0.7564 | 43.2877 |
74
- | 0.0004 | 2.34 | 1500 | 0.7580 | 43.8280 |
75
- | 0.0004 | 2.49 | 1600 | 0.7626 | 43.5173 |
76
- | 0.019 | 2.65 | 1700 | 0.7654 | 43.7677 |
77
- | 0.0004 | 2.8 | 1800 | 0.7679 | 43.8001 |
78
- | 0.0003 | 2.96 | 1900 | 0.7694 | 43.7491 |
79
- | 0.0003 | 3.12 | 2000 | 0.7713 | 43.8906 |
80
- | 0.0003 | 3.27 | 2100 | 0.7737 | 43.7978 |
81
- | 0.0003 | 3.43 | 2200 | 0.7763 | 43.6031 |
82
- | 0.0003 | 3.58 | 2300 | 0.7770 | 43.9253 |
83
- | 0.0003 | 3.74 | 2400 | 0.7778 | 43.9995 |
84
- | 0.0003 | 3.9 | 2500 | 0.7780 | 44.0946 |
85
- | 0.0003 | 4.05 | 2600 | 0.7787 | 43.8906 |
86
- | 0.0156 | 4.21 | 2700 | 0.7798 | 43.9091 |
87
- | 0.0003 | 4.36 | 2800 | 0.7805 | 43.9114 |
88
- | 0.0003 | 4.52 | 2900 | 0.7809 | 43.9230 |
89
- | 0.0003 | 4.67 | 3000 | 0.7811 | 43.9230 |
90
 
91
 
92
  ### Framework versions
 
22
 
23
  This model is a fine-tuned version of [makhataei/Whisper-Small-Common-Voice](https://huggingface.co/makhataei/Whisper-Small-Common-Voice) on the Common Voice 16.0 dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 0.7215
26
+ - Wer: 43.6054
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 1e-07
46
  - train_batch_size: 10
47
  - eval_batch_size: 10
48
  - seed: 42
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer |
59
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
60
+ | 0.0006 | 0.16 | 100 | 0.7099 | 42.5759 |
61
+ | 0.0016 | 0.31 | 200 | 0.7139 | 42.6710 |
62
+ | 0.0051 | 0.47 | 300 | 0.7114 | 42.6803 |
63
+ | 0.004 | 0.62 | 400 | 0.7109 | 42.6130 |
64
+ | 0.0047 | 0.78 | 500 | 0.7101 | 42.3139 |
65
+ | 0.0029 | 0.93 | 600 | 0.7105 | 42.4113 |
66
+ | 0.0016 | 1.09 | 700 | 0.7101 | 42.4067 |
67
+ | 0.0016 | 1.25 | 800 | 0.7129 | 42.3997 |
68
+ | 0.0028 | 1.4 | 900 | 0.7145 | 42.3951 |
69
+ | 0.0019 | 1.56 | 1000 | 0.7135 | 42.3557 |
70
+ | 0.0019 | 1.71 | 1100 | 0.7132 | 42.3534 |
71
+ | 0.0021 | 1.87 | 1200 | 0.7128 | 42.4739 |
72
+ | 0.0023 | 2.03 | 1300 | 0.7144 | 42.9330 |
73
+ | 0.0021 | 2.18 | 1400 | 0.7151 | 42.8403 |
74
+ | 0.0019 | 2.34 | 1500 | 0.7158 | 42.8820 |
75
+ | 0.0014 | 2.49 | 1600 | 0.7166 | 42.9121 |
76
+ | 0.0262 | 2.65 | 1700 | 0.7171 | 42.9933 |
77
+ | 0.0022 | 2.8 | 1800 | 0.7183 | 42.9608 |
78
+ | 0.0012 | 2.96 | 1900 | 0.7185 | 43.3921 |
79
+ | 0.0018 | 3.12 | 2000 | 0.7187 | 43.3295 |
80
+ | 0.0015 | 3.27 | 2100 | 0.7191 | 43.3480 |
81
+ | 0.0013 | 3.43 | 2200 | 0.7198 | 43.3898 |
82
+ | 0.0019 | 3.58 | 2300 | 0.7200 | 43.4106 |
83
+ | 0.0017 | 3.74 | 2400 | 0.7206 | 43.4315 |
84
+ | 0.0015 | 3.9 | 2500 | 0.7209 | 43.4268 |
85
+ | 0.0016 | 4.05 | 2600 | 0.7210 | 43.6031 |
86
+ | 0.0267 | 4.21 | 2700 | 0.7212 | 43.5891 |
87
+ | 0.001 | 4.36 | 2800 | 0.7213 | 43.5938 |
88
+ | 0.0015 | 4.52 | 2900 | 0.7215 | 43.6031 |
89
+ | 0.0019 | 4.67 | 3000 | 0.7215 | 43.6054 |
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f1f3bdf7e61dba3392cdddc9aeb4e704f90bbfbc5dc6233e1a2a87b6b168ace
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b17c2202dae29457932aab017fd6a160bc37f2181c632b3ca150e7227d4b3e
3
  size 966995080
runs/Jan05_01-51-40_Software-AI/events.out.tfevents.1704406903.Software-AI.4154976.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:006bfeb4295cf128377c3c5ff7dc5e87c576c2f38c2d09a62b62b3ab47141f0f
3
- size 30603
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:769f4be2e1664d54bf3c8df027817584d4552802ac4842a3d3a744eb8ad72c1c
3
+ size 33795