# 16kHz Audio Adaptation

A Telugu automatic speech recognition model based on OpenAI Whisper-small architecture, optimized for Indian languages by the ARTPARK-IISc team

Keyword detection model based on Hubert-Large architecture, excelling in SUPERB benchmark tests

A base Wav2Vec2 model pretrained on 100 hours of unlabeled Vietnamese speech audio from the VLSP dataset, requiring fine-tuning for downstream tasks.

A Bengali automatic speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, trained using OpenSLR dataset.

SEW-tiny is a compressed and efficient speech pretraining model developed by ASAPP Research, pretrained on 16kHz sampled speech audio, suitable for various downstream speech tasks.

Fine-tuned based on Facebook's wav2vec2-large-xlsr-53 model, supporting automatic speech recognition tasks for Hindi and Marathi

A speech recognition model based on Microsoft's UniSpeech architecture, specifically fine-tuned for the Kyrgyz language

SEW-D-base+ is an efficient speech recognition model developed by ASAPP Research, pre-trained on 16kHz sampled speech audio, and excels on the LibriSpeech dataset.