Finnish-NLP/whisper-tiny-finnish

Model

should probably proofread and complete it, then remove this comment. -->

13 commits

1 linked in READMEs

updated Jan 6, 2024

See the code

automatic-speech-recognition

endpoints_compatible

generated_from_trainer

model-index

safetensors

transformers

whisper

whisper-event

README

WhisperTinyFinnishV3

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

Loss: 0.5363
Wer: 45.1376

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: 3e-06
train_batch_size: 32
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
training_steps: 10000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9236	0.1	1000	0.7783	58.5187
0.727	0.2	2000	0.6638	53.1097
0.6867	0.3	3000	0.6113	50.2639
0.8348	0.4	4000	0.5882	48.2661
0.5165	0.5	5000	0.5679	47.1259
0.5509	0.6	6000	0.5540	46.6359
0.639	0.7	7000	0.5466	46.5228
0.4715	0.8	8000	0.5400	45.9763
0.6306	0.9	9000	0.5363	45.1376
0.4598	1.0	10000	0.5352	45.4768

Framework versions

Transformers 4.36.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0

Contributors

RASMUS

13 commits

Similar repos

dominguesm/whisper-tiny-pt

Model

should probably proofread and complete it, then remove this comment. -->

sanchit-gandhi/whisper-small-hi

Model

should probably proofread and complete it, then remove this comment. -->

Bajiyo/w2v-bert-2.0-nonstudio_and_studioRecords_final

Model

should probably proofread and complete it, then remove this comment. -->

RASMUS/whisper-small-fi

Model

speech31/wav2vec2-large-english-TIMIT-phoneme_v3

Model

should probably proofread and complete it, then remove this comment. -->

jonatasgrosman/wav2vec2-large-xlsr-53-finnish

Model

Fine-tuned XLSR-53 large model for speech recognition in Finnish

GoshKolotyan/w2v-bert-2.0-armenian-CV16.0-version-demo

Model

should probably proofread and complete it, then remove this comment. -->

cy0307/c-whisper-finetune

Model

Whisper — fine-tune ASR 🚧 not trained yet

Linked in READMEs

paazmaya/speak-finnish-get-portuguese

Finnish to Portuguese Speech Translation

README badge

Finnish-NLP/whisper-tiny-finnish

Model

should probably proofread and complete it, then remove this comment. -->

13 commits

1 linked in READMEs

updated Jan 6, 2024

See the code

automatic-speech-recognition

endpoints_compatible

generated_from_trainer

model-index

safetensors

transformers

whisper

whisper-event

README

WhisperTinyFinnishV3

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

Loss: 0.5363
Wer: 45.1376

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: 3e-06
train_batch_size: 32
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
training_steps: 10000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9236	0.1	1000	0.7783	58.5187
0.727	0.2	2000	0.6638	53.1097
0.6867	0.3	3000	0.6113	50.2639
0.8348	0.4	4000	0.5882	48.2661
0.5165	0.5	5000	0.5679	47.1259
0.5509	0.6	6000	0.5540	46.6359
0.639	0.7	7000	0.5466	46.5228
0.4715	0.8	8000	0.5400	45.9763
0.6306	0.9	9000	0.5363	45.1376
0.4598	1.0	10000	0.5352	45.4768