README.md

metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - ASR
  - Papiamentu
  - Whisper
  - Speech Recognition
  - generated_from_trainer
datasets:
  - sonnygeorge/papi_asr_corpus
metrics:
  - wer
model-index:
  - name: Whisper Tiny Papiamentu
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Papi ASR
          type: sonnygeorge/papi_asr_corpus
        metrics:
          - name: Wer
            type: wer
            value: 43.55778449738181

Whisper Tiny Papiamentu

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

• Loss: 0.5097
• Wer: 43.5578
• Cer: 21.6799

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 3
• training_steps: 150
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.5202	0.07	50	0.6086	53.0423	30.5887
0.4887	0.15	100	0.5316	45.0254	21.4973
0.4872	0.22	150	0.5097	43.5578	21.6799

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0