VladS159/Whisper_medium_ro_VladS_1000_steps_multi_gpu_25_02_2024

Whisper Medium Ro - Sarbu Vlad - multi gpu

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 16.1 + Romanian speech synthesis dataset. It achieves the following results on the evaluation set:

• Loss: 0.1247
• Wer: 11.7262

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: 10
• eval_batch_size: 10
• seed: 42
• distributed_type: multi-GPU
• num_devices: 3
• total_train_batch_size: 30
• total_eval_batch_size: 30
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1447	0.61	250	0.1532	13.8768
0.0599	1.23	500	0.1305	12.5141
0.0595	1.84	750	0.1256	12.3255
0.032	2.46	1000	0.1247	11.7262

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.17.0
• Tokenizers 0.15.1