You can deploy this model and start earning money today!

emilios/
whisper-sm-farsipal-e7

Name: whisper-sm-farsipal-e7
Availability: InStock

automatic-speech-recognition

whisper-event

generated_from_trainer

apache-2.0

endpoints_compatible

Views

No views yet

Whisper small Greek Farsipal and El Greco

This model is a fine-tuned version of emilios/whisper-sm-farsipal-e5 on the mozilla-foundation/common_voice_11_0,google/fleurs el,el_gr dataset. It achieves the following results on the evaluation set:

Loss: 0.5015
Wer: 16.4933

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-06
train_batch_size: 32
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0004	2.49	1000	0.4797	16.7348
0.0003	4.98	2000	0.4895	16.5397
0.0002	7.46	3000	0.4963	16.5119
0.0002	9.95	4000	0.5015	16.4933
0.0002	12.44	5000	0.5034	16.5676

Framework versions

Transformers 4.26.0.dev0
Pytorch 2.0.0.dev20221216+cu116
Datasets 2.7.1.dev0
Tokenizers 0.13.2

emilios/whisper-sm-farsipal-e7

Whisper small Greek Farsipal and El Greco

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

emilios/
whisper-sm-farsipal-e7