This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 fi dataset. It achieves the following results on the evaluation set:

Loss: 0.3010
Wer: 15.7181

Model description

The Model is fine-tuned for 1000 steps/updates on CV11 Finnish train+valiation data.

Zero-shot - 18.8 (CV9 test data, even on CV11 the WER is closer a bit higher than this)
Fine-tuned - 15.71 (CV11 test data)

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: 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: 500
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0009	19.01	1000	0.3010	15.7181

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0+cu117
Datasets 2.7.1.dev0
Tokenizers 0.13.2

sgangireddy/whisper-medium-cv-fi

Whisper medium Finnish CV