Hugging Face's logo

procit006
/
whisper-small-nl-v0.7-17

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Dutch
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-nl-v0.7-17 / README.md
Rakshya Bhetwal
Update README.md
2e08bfa verified
preview code
|
raw
history blame contribute delete
No virus
1.48 kB
metadata
language:
  - nl
license: apache-2.0
base_model: rb00/whisper-small-nl-v0.4
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
  - mozilla-foundation/common_voice_16_0
  - mozilla-foundation/common_voice_17_0
model-index:
  - name: Whisper Small
    results: []

Whisper Small

This model is a fine-tuned version of rb00/whisper-small-nl-v0.4 on the Common Voice 17.0 dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

For 100 samples:

  • wer (dutch_stc_speaker_by_susan_upto_03_jun): 11.5385
  • wer (HouseAndZipCodeSpeechgen): 42.2128
  • wer (facebook/multilingual_librispeech): 42.1868

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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: 50
  • training_steps: 100
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1