Whisper Small Yoruba

🚀 Whisper_small_Yoruba

This model is a fine - tuned version of openai/whisper-small on the google/fleurs yo_ng dataset. It can be used for automatic speech recognition tasks, achieving certain performance on the evaluation set.

🚀 Quick Start

This section provides a high - level overview of the model's performance and basic information. The model is fine - tuned on the google/fleurs yo_ng dataset and has the following evaluation results:

• Loss: 1.6773
• Wer: 67.8866

📚 Documentation

Model Information

Training and Evaluation

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e - 05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• distributed_type: multi - GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Training Results

Framework Versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2

📄 License

This model is licensed under the Apache 2.0 license.