Hugging Face's logo

vargha
/
Hubert-fine-tuned-persian

Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
vargha commited on
Commit
6da9dd9
·
verified ·
1 Parent(s): d96d976

vargha/Hubert-fine-tuned-persian

Browse files
Files changed (5) hide show
  1. README.md +19 -17
  2. model.safetensors +1 -1
  3. runs/Dec26_01-31-50_v-lab/events.out.tfevents.1735164110.v-lab.1593451.0 +3 -0
  4. runs/Dec26_01-31-50_v-lab/events.out.tfevents.1735165859.v-lab.1593451.1 +3 -0
  5. training_args.bin +2 -2
README.md CHANGED
@@ -21,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [m3hrdadfi/hubert-base-persian-speech-emotion-recognition](https://huggingface.co/m3hrdadfi/hubert-base-persian-speech-emotion-recognition) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.5590
25
- - Accuracy: 0.7381
26
- - Precision: 0.7568
27
- - Recall: 0.6269
28
- - F1: 0.6857
29
- - Precision Neutral: 0.7268
30
- - Recall Neutral: 0.8313
31
- - F1 Neutral: 0.7755
32
- - Precision Anger: 0.7568
33
- - Recall Anger: 0.6269
34
- - F1 Anger: 0.6857
35
 
36
  ## Model description
37
 
@@ -50,22 +50,24 @@ More information needed
50
  ### Training hyperparameters
51
 
52
  The following hyperparameters were used during training:
53
- - learning_rate: 3e-05
54
  - train_batch_size: 4
55
  - eval_batch_size: 4
56
  - seed: 42
57
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
58
- - lr_scheduler_type: cosine
59
  - lr_scheduler_warmup_steps: 500
60
- - num_epochs: 3
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Precision Neutral | Recall Neutral | F1 Neutral | Precision Anger | Recall Anger | F1 Anger |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|
66
- | 0.7377 | 1.0 | 294 | 0.6635 | 0.5748 | 0.5213 | 0.8209 | 0.6377 | 0.7108 | 0.3688 | 0.4856 | 0.5213 | 0.8209 | 0.6377 |
67
- | 0.6582 | 2.0 | 588 | 0.5978 | 0.7007 | 0.6769 | 0.6567 | 0.6667 | 0.7195 | 0.7375 | 0.7284 | 0.6769 | 0.6567 | 0.6667 |
68
- | 0.405 | 3.0 | 882 | 0.5590 | 0.7381 | 0.7568 | 0.6269 | 0.6857 | 0.7268 | 0.8313 | 0.7755 | 0.7568 | 0.6269 | 0.6857 |
 
 
69
 
70
 
71
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [m3hrdadfi/hubert-base-persian-speech-emotion-recognition](https://huggingface.co/m3hrdadfi/hubert-base-persian-speech-emotion-recognition) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.5445
25
+ - Accuracy: 0.7483
26
+ - Precision: 0.7
27
+ - Recall: 0.7836
28
+ - F1: 0.7394
29
+ - Precision Neutral: 0.7986
30
+ - Recall Neutral: 0.7188
31
+ - F1 Neutral: 0.7566
32
+ - Precision Anger: 0.7
33
+ - Recall Anger: 0.7836
34
+ - F1 Anger: 0.7394
35
 
36
  ## Model description
37
 
 
50
  ### Training hyperparameters
51
 
52
  The following hyperparameters were used during training:
53
+ - learning_rate: 2.5e-05
54
  - train_batch_size: 4
55
  - eval_batch_size: 4
56
  - seed: 42
57
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
58
+ - lr_scheduler_type: reduce_lr_on_plateau
59
  - lr_scheduler_warmup_steps: 500
60
+ - num_epochs: 5
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Precision Neutral | Recall Neutral | F1 Neutral | Precision Anger | Recall Anger | F1 Anger |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|
66
+ | 0.7337 | 1.0 | 294 | 0.6602 | 0.5816 | 0.5216 | 0.9925 | 0.6838 | 0.9744 | 0.2375 | 0.3819 | 0.5216 | 0.9925 | 0.6838 |
67
+ | 0.5922 | 2.0 | 588 | 0.5445 | 0.7483 | 0.7 | 0.7836 | 0.7394 | 0.7986 | 0.7188 | 0.7566 | 0.7 | 0.7836 | 0.7394 |
68
+ | 0.4774 | 3.0 | 882 | 0.7353 | 0.7177 | 0.7257 | 0.6119 | 0.6640 | 0.7127 | 0.8063 | 0.7566 | 0.7257 | 0.6119 | 0.6640 |
69
+ | 0.4527 | 4.0 | 1176 | 0.6275 | 0.7143 | 0.6582 | 0.7761 | 0.7123 | 0.7794 | 0.6625 | 0.7162 | 0.6582 | 0.7761 | 0.7123 |
70
+ | 0.5922 | 5.0 | 1470 | 0.8464 | 0.7347 | 0.6647 | 0.8433 | 0.7434 | 0.8306 | 0.6438 | 0.7254 | 0.6647 | 0.8433 | 0.7434 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6752dd99c7b380b89e84ce65df96baf0dc6e7f4a3c0e89f731bf798aa37e6867
3
  size 379881088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a993a68b6551bf9e373cf3744cea8567eb180b7628bd90ecdf78828f81c2cfe2
3
  size 379881088
runs/Dec26_01-31-50_v-lab/events.out.tfevents.1735164110.v-lab.1593451.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487d08d1d284c205a0bf2820a57ebc6b8728b5ac3a45f8798cd90cd9a3706740
3
+ size 20928
runs/Dec26_01-31-50_v-lab/events.out.tfevents.1735165859.v-lab.1593451.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383f66d301c1ad65708962d51ce7155b894185cba20c56ced60fadc9fb33b3a6
3
+ size 900
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00d94207479255651fbd23ed2b65cf0fc01e81ce94d8fa7087378e076262a878
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:368cfd855387bb267c5229994153f6ffbca07a1bd46cfb3829650fa9a3ed8877
3
+ size 5432