neurlang
/

ipa-whisper-base

Automatic Speech Recognition

Eval Results (legacy)

Model card Files Files and versions

neurlang commited on Apr 11, 2025

Commit

32dabb0

·

verified ·

1 Parent(s): 2941b9d

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -163,8 +163,8 @@ base_model:
 # Whisper IPA
 Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Fine-tuned on 15000 wavs
-of labelled IPA data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need
-for fine-tuning.
 Whisper was proposed in the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)
 by Alec Radford et al from OpenAI. The original code repository can be found [here](https://github.com/openai/whisper).

 # Whisper IPA
 Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Fine-tuned on 15000 wavs
+of labelled synthetic IPA data (generated using the goruut 0.6.2 phonemizer), Whisper models demonstrate a strong ability
+to generalise to many languages, datasets and domains **without** the need for fine-tuning.
 Whisper was proposed in the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)
 by Alec Radford et al from OpenAI. The original code repository can be found [here](https://github.com/openai/whisper).