Ahmed107/hamsa-meetingsv2.3

Hamsa-meetings

This model is a fine-tuned version of nadsoft/hamsa-v0.1-beta on the nadsoft/nadsoft-meetings dataset. It achieves the following results on the evaluation set:

• Loss: 0.7825
• Wer Ortho: 38.5890
• Wer: 38.5890

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: 6.25e-06
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.3968	2.33	100	0.6252	40.3067	40.3067
0.0793	4.65	200	0.6724	40.0	40.0
0.0171	6.98	300	0.7306	38.2209	38.2209
0.0054	9.3	400	0.7718	38.8957	38.8957
0.0038	11.63	500	0.7825	38.5890	38.5890

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0