Whisper Small Yoruba - Bola Ologundudu

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.2225
• Wer: 70.6135

Model description

from transformers import pipeline import torch

modelName="ajibs75/whisper-small-yoruba" device = 0 if torch.cuda.is_available() else "cpu" pipe = pipeline(task="automatic-speech-recognition",model=modelName,chunk_length_s=30,device=device,) pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="yo", task="transcribe")

audio = "sample.mp3" text = pipe(audio) transacribed_audio = text["text"] print(transacribed_audio)

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: 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: 4000
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.42.4
• Pytorch 2.1.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1