Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-tiny_v2.1-ro – AI Model by giigii91 | AlphaNeural AI
You can deploy this model and start earning money today!
giigii91
/
whisper-tiny_v2.1-ro
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
ro
mozilla-foundation/common_voice_11_0
openai/whisper-tiny
finetune
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Tiny RO - Georgescu Dumitru
This model is a fine-tuned version of
openai/whisper-tiny
on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
Loss: 0.4606
Wer: 37.7291
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-08
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
11.2437
1.7986
1000
0.4601
37.6053
10.9474
3.5971
2000
0.4602
37.0002
10.736
5.3957
3000
0.4604
37.5310
10.6145
7.1942
4000
0.4605
37.7114
10.5325
8.9928
5000
0.4606
37.7291
Framework versions
Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1
