AMI - Wav2Vec2-Large-LV60

Trained on < 2 epochs, see run.sh.

Results: Validation:

{
    "eval_loss": 0.599422812461853,
    "eval_runtime": 197.9157,
    "eval_samples": 12383,
    "eval_samples_per_second": 62.567,
    "eval_steps_per_second": 0.98,
    "eval_wer": 0.25275729434515587
}

Eval:

    "eval_loss": 0.5091261863708496,
    "eval_runtime": 208.7241,
    "eval_samples": 11944,
    "eval_samples_per_second": 57.224,
    "eval_steps_per_second": 0.896,
    "eval_wer": 0.2521060666025895

Downloads last month: 7

Inference Examples

Automatic Speech Recognition

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.