whisper-base-full-data-aug-v1 – AI Model by thanhduycao | AlphaNeural AI

You can deploy this model and start earning money today!

thanhduycao/
whisper-base-full-data-aug-v1

like

0

automatic-speech-recognition

generated_from_trainer

endpoints_compatible

Views

No views yet

whisper-base-full-data-aug-v1

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3136

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
distributed_type: tpu
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 256
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 5000
training_steps: 63840

Training results

Training Loss	Epoch	Step	Validation Loss
0.4148	1.57	5000	0.6040
0.3061	3.13	10000	0.4816
0.2601	4.7	15000	0.4329
0.2315	6.27	20000	0.3968
0.2186	7.83	25000	0.3744
0.1992	9.4	30000	0.3563
0.193	10.97	35000	0.3501
0.1812	12.53	40000	0.3445
0.1733	14.1	45000	0.3366
0.1661	15.67	50000	0.3241
0.1604	17.23	55000	0.3168
0.1562	18.8	60000	0.3159

Framework versions

Transformers 4.28.1
Pytorch 2.1.0a0+gitcc01568
Datasets 2.13.1
Tokenizers 0.13.3