Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-v3-turbo-swahili-english – AI Model by Godsonntungi2 | AlphaNeural AI
You can deploy this model and start earning money today!
Godsonntungi2
/
whisper-v3-turbo-swahili-english
like
0
peft
safetensors
adapter
lora
transformers
openai/whisper-large-v3-turbo
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-v3-turbo-swahili-english
This model is a fine-tuned version of
openai/whisper-large-v3-turbo
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.4650
Wer: 27.9621
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: 0.0001
train_batch_size: 8
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.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_ratio: 0.1
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.559
0.8850
50
0.5116
28.0806
0.4667
1.7611
100
0.4733
27.9621
0.4055
2.6372
150
0.4650
27.9621
Framework versions
PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 2.21.0
Tokenizers 0.22.1
