Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
finetuning-whisper-tiny-swahili-ablation_ndizi_CV – AI Model by smutuvi | AlphaNeural AI
You can deploy this model and start earning money today!
smutuvi
/
finetuning-whisper-tiny-swahili-ablation_ndizi_CV
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
openai/whisper-tiny
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
finetuning-whisper-tiny-swahili-ablation_ndizi_CV
This model is a fine-tuned version of
openai/whisper-tiny
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.9389
Wer: 80.6691
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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.9372
1.6987
1000
1.0468
75.5567
0.7027
3.3961
2000
0.9675
73.3760
0.6545
5.0935
3000
0.9433
82.0182
0.627
6.7922
4000
0.9389
80.6691
Framework versions
Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.22.1
