Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-base-wer – AI Model by adrianSauer | AlphaNeural AI
You can deploy this model and start earning money today!
adrianSauer
/
whisper-base-wer
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
gn
mozilla-foundation/common_voice_16_1
openai/whisper-base
finetune
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Common Voice 16 - Guarani
This model is a fine-tuned version of
openai/whisper-base
on the Common Voice 16 dataset. It achieves the following results on the evaluation set:
Loss: 0.5857
Wer: 58.1798
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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 500
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
2.3905
1.0101
100
0.9598
81.9654
0.5779
2.0202
200
0.6883
68.6767
0.3116
3.0303
300
0.5997
62.5349
0.1741
4.0404
400
0.5750
59.5757
0.0955
5.0505
500
0.5857
58.1798
Framework versions
Transformers 4.44.0
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1
