Automatic International Phonetic Alphabet Transcription

This demo allows you to experiment with producing phonetic transcriptions of uploaded or recorded audio using a selected automatic speech recognition (ASR) model.

If you're unsure which model to use, the default ginic/full_dataset_train_3_wav2vec2-large-xlsr-53-buckeye-ipa should give good performance.

IPA transcription ASR model

Select the model to use for prediction.

Transcription Type

IPA Transcriptions

IPA Transcriptions
Source Tier (existing)