You can deploy this model and start earning money today!

marccgrau/
whisper-small-allSNR-v4

Name: whisper-small-allSNR-v4
Availability: InStock

transformers

pytorch

whisper

automatic-speech-recognition

sbb-asr

generated_from_trainer

marccgrau/sbbdata_allSNR

apache-2.0

model-index

endpoints_compatible

Views

No views yet

Whisper Small German SBB all SNR - v4

This model is a fine-tuned version of openai/whisper-small on the SBB Dataset 05.01.2023 dataset. It achieves the following results on the evaluation set:

Loss: 0.0287
Wer: 0.0222

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: 5e-06
train_batch_size: 64
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
training_steps: 700
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.6894	0.71	100	0.4702	0.4661
0.1896	1.42	200	0.0322	0.0241
0.0297	2.13	300	0.0349	0.0228
0.0181	2.84	400	0.0250	0.0209
0.0154	3.55	500	0.0298	0.0209
0.0112	4.26	600	0.0327	0.0222
0.009	4.96	700	0.0287	0.0222

Framework versions

Transformers 4.25.1
Pytorch 1.13.1
Datasets 2.8.0
Tokenizers 0.12.1

marccgrau/whisper-small-allSNR-v4

Whisper Small German SBB all SNR - v4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

marccgrau/
whisper-small-allSNR-v4