whisper-tiny_to_portuguese_accent – AI Model by lilpharaoh1 | AlphaNeural AI

You can deploy this model and start earning money today!

lilpharaoh1/
whisper-tiny_to_portuguese_accent

like

0

automatic-speech-recognition

hf-asr-leaderboard

generated_from_trainer

portuguese_english

openai/whisper-tiny

endpoints_compatible

Views

No views yet

Whisper tiny Portuguese

This model is a fine-tuned version of openai/whisper-tiny on the Portuguese English dataset. It achieves the following results on the evaluation set:

Loss: 0.2749
Wer: 11.6496

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: 2
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 500
training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2852	0.4608	500	0.2970	14.5573
0.2525	0.9217	1000	0.2792	12.8611
0.0976	1.3825	1500	0.2679	12.4138
0.1154	1.8433	2000	0.2597	11.5005
0.0241	2.3041	2500	0.2742	12.2833
0.0202	2.7650	3000	0.2725	11.9105
0.036	3.2258	3500	0.2745	11.9478
0.0041	3.6866	4000	0.2749	11.6496

Framework versions

Transformers 4.50.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0