goaicorp/mos-whisper-small

Whisper Small mos - GO AI CORP

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

• Loss: 0.3758
• Wer: 38.6498

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: 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

Training Loss	Epoch	Step	Validation Loss	Wer
0.5472	0.7758	1000	0.5230	51.5711
0.3553	1.5516	2000	0.4258	44.0868
0.1974	2.3274	3000	0.3896	40.7922
0.1456	3.1032	4000	0.3758	38.6498

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0