steja/whisper-small-somali

Whisper_small_Somali

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

• Loss: 2.0764
• Wer: 66.5950

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: 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

Training Loss	Epoch	Step	Validation Loss	Wer
0.0205	30.74	400	1.8418	67.2524
0.0012	61.52	800	2.0764	66.5950
0.0006	92.3	1200	2.1537	67.6452
0.0004	123.07	1600	2.1930	67.1367
0.0004	153.81	2000	2.2065	66.9299

Framework versions

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