README.md

metadata

language:
  - sl
license: apache-2.0
base_model: openai/whisper-small
tags:
  - asr-sl
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
model-index:
  - name: sl-asr-model-primary-small
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 13.0
          type: mozilla-foundation/common_voice_13_0
          args: 'config: sl, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 0.3198070374574347

sl-asr-model-primary-small

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

• Loss: 0.3394
• Wer: 0.3198

Model description

Slovenian-ASR-model-primary, 242M paramerters

Intended uses & limitations

Automatic speech recognition for Slovenian

Training and evaluation data

EWCH/data-preprocessed-commonvoice-sl-80s

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.001
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3415	1.0	650	0.3394	0.3198

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1
• Datasets 2.17.1
• Tokenizers 0.15.2