finetune_v14 – AI Model by tz3 | AlphaNeural AI

You can deploy this model and start earning money today!

tz3/
finetune_v14

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-large-v3

endpoints_compatible

Views

No views yet

finetune_v14

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6836
Wer: 39.4400

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: 4
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 8
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 5
training_steps: 80
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	7.2727	10	0.6533	30.4626
No log	14.5455	20	0.6367	29.8539
No log	21.8182	30	0.6772	29.5192
No log	29.0909	40	0.6792	34.9057
0.1995	36.3636	50	0.6777	180.6147
0.1995	43.6364	60	0.6782	33.9318
0.1995	50.9091	70	0.6821	37.4924
0.1995	58.1818	80	0.6836	39.4400

Framework versions

Transformers 4.42.4
Pytorch 2.2.0
Datasets 2.20.0
Tokenizers 0.19.1