discoverylabs/whisper-small-cpu-finetuned

Whisper Small CPU Finetuned

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

• Loss: 0.8936
• Wer: 0.0

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8939	0.5	5	0.9602	0.0
0.7066	1.0	10	0.8936	0.0

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cpu
• Datasets 2.16.1
• Tokenizers 0.15.1