Hugging Face's logo

mahmoudmamdouh13
/
ast-finetuned-en-alphabets

Audio Classification
Transformers
TensorBoard
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
mahmoudmamdouh13 commited on
Commit
593753a
·
verified ·
1 Parent(s): db0690e

End of training

Browse files
Files changed (3) hide show
  1. README.md +6 -7
  2. model.safetensors +1 -1
  3. runs/Jun26_19-39-56_ip-10-192-11-139/events.out.tfevents.1750966808.ip-10-192-11-139.33880.1 +2 -2
README.md CHANGED
@@ -41,7 +41,7 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [MIT/ast-finetuned-speech-commands-v2](https://huggingface.co/MIT/ast-finetuned-speech-commands-v2) on the audiofolder dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.2165
45
  - Precision: 0.9651
46
  - Recall: 0.9481
47
  - F1: 0.9476
@@ -70,18 +70,17 @@ The following hyperparameters were used during training:
70
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
71
  - lr_scheduler_type: linear
72
  - lr_scheduler_warmup_ratio: 0.1
73
- - num_epochs: 5
74
  - mixed_precision_training: Native AMP
75
 
76
  ### Training results
77
 
78
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
79
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
80
- | 0.3603 | 1.0 | 113 | 0.2447 | 0.9452 | 0.9292 | 0.9261 |
81
- | 0.1769 | 2.0 | 226 | 0.1663 | 0.9611 | 0.9434 | 0.9429 |
82
- | 0.0282 | 3.0 | 339 | 0.1778 | 0.9606 | 0.9481 | 0.9475 |
83
- | 0.0106 | 4.0 | 452 | 0.2003 | 0.9735 | 0.9623 | 0.9629 |
84
- | 0.0055 | 5.0 | 565 | 0.2165 | 0.9651 | 0.9481 | 0.9476 |
85
 
86
 
87
  ### Framework versions
 
41
 
42
  This model is a fine-tuned version of [MIT/ast-finetuned-speech-commands-v2](https://huggingface.co/MIT/ast-finetuned-speech-commands-v2) on the audiofolder dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.1933
45
  - Precision: 0.9651
46
  - Recall: 0.9481
47
  - F1: 0.9476
 
70
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
71
  - lr_scheduler_type: linear
72
  - lr_scheduler_warmup_ratio: 0.1
73
+ - num_epochs: 4
74
  - mixed_precision_training: Native AMP
75
 
76
  ### Training results
77
 
78
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
79
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
80
+ | 0.3705 | 1.0 | 113 | 0.2441 | 0.9566 | 0.9434 | 0.9432 |
81
+ | 0.1728 | 2.0 | 226 | 0.1617 | 0.9608 | 0.9481 | 0.9478 |
82
+ | 0.0321 | 3.0 | 339 | 0.1838 | 0.9651 | 0.9481 | 0.9476 |
83
+ | 0.011 | 4.0 | 452 | 0.1933 | 0.9651 | 0.9481 | 0.9476 |
 
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b0e484551d8aa3fd11ecc1a7f86f756ee5709d7462af75a692cdb349fc75761
3
  size 341589120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6797228425478a70482b231041ab2a3ae25d8eb6a5cfebceb19c3c89b91bf9a
3
  size 341589120
runs/Jun26_19-39-56_ip-10-192-11-139/events.out.tfevents.1750966808.ip-10-192-11-139.33880.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7e3bf8aacd083684b20c11ead35bb99ae7cc36a1887f9fdc050c65fe08f0dd8
3
- size 21441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e89b3cf8289cd6071fcd6b8fde89c550a33f33853e0fa0a3fe8e551479da75
3
+ size 26857