alianurrahman commited on
Commit
56f55ac
1 Parent(s): 1fcfcf1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -22,7 +22,7 @@ for a Speech Emotion Recognition (SER) task.
22
 
23
  The dataset used to fine-tune the original pre-trained model is
24
  the [RAVDESS dataset](https://zenodo.org/record/1188976#.YO6yI-gzaUk). This dataset provides 1440 samples of recordings
25
- from actors performing on 8 different emotions in English, which are:
26
 
27
  ```python
28
  emotions = ['angry', 'disgust', 'fear', 'happy', 'sad']
@@ -51,15 +51,15 @@ More information needed
51
 
52
  The following hyperparameters were used during training:
53
 
54
- - learning_rate: 0.0001
55
- - train_batch_size: 4
56
- - eval_batch_size: 4
57
  - seed: 42
58
  - gradient_accumulation_steps: 2
59
- - total_train_batch_size: 8
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
- - num_epochs: 3
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
@@ -84,11 +84,11 @@ The following hyperparameters were used during training:
84
  ## Citation
85
 
86
  ```bibtex
87
- @misc {enrique_hernández_calabrés_2024,
88
  author = { {Alianur Rahman} },
89
- title = { wav2vec2-base-en-speech-emotion-recognition (Revision 17cf17c) },
90
  year = 2024,
91
- url = { https://huggingface.co/alianurrahman/model }
92
  }
93
  ```
94
 
 
22
 
23
  The dataset used to fine-tune the original pre-trained model is
24
  the [RAVDESS dataset](https://zenodo.org/record/1188976#.YO6yI-gzaUk). This dataset provides 1440 samples of recordings
25
+ from actors performing on 5 different emotions in Bahasa Indonesia, which are:
26
 
27
  ```python
28
  emotions = ['angry', 'disgust', 'fear', 'happy', 'sad']
 
51
 
52
  The following hyperparameters were used during training:
53
 
54
+ - learning_rate: 3e-5
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
  - seed: 42
58
  - gradient_accumulation_steps: 2
59
+ - total_train_batch_size: 10
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - num_epochs: 10
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
 
84
  ## Citation
85
 
86
  ```bibtex
87
+ @misc {alianur_rahman_2024,
88
  author = { {Alianur Rahman} },
89
+ title = { wav2vec2-base-indonesian-speech-emotion-recognition (Revision 1fcfcf1) },
90
  year = 2024,
91
+ url = { https://huggingface.co/alianurrahman/wav2vec2-base-indonesian-speech-emotion-recognition }
92
  }
93
  ```
94