You can deploy this model and start earning money today!

Jamin20/
whisper-fine-tuning_lon

Name: whisper-fine-tuning_lon
Availability: InStock

automatic-speech-recognition

hf-asr-leaderboard

generated_from_trainer

mozilla-foundation/common_voice_11_0

model-index

endpoints_compatible

Views

No views yet

whisper-fine-tuned-de_learn

This model is a fine-tuned version of whisper-fine-tuned-de_arg_new on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.3423
Wer: 14.3297

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: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 8000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2689	0.67	1000	0.3094	15.5378
0.1072	1.33	2000	0.3068	15.0653
0.1134	2.0	3000	0.2991	14.5704
0.0437	2.67	4000	0.3166	14.8876
0.0163	3.33	5000	0.3308	14.4940
0.0118	4.0	6000	0.3314	14.3882
0.0052	4.67	7000	0.3399	14.2915
0.0032	5.33	8000	0.3423	14.3297

Framework versions

Transformers 4.28.0.dev0
Pytorch 2.0.0
Datasets 2.11.0
Tokenizers 0.13.3

Jamin20/whisper-fine-tuning_lon

whisper-fine-tuned-de_learn

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jamin20/
whisper-fine-tuning_lon