# High Accuracy ASR

GigaAM-v2-CTC is a Russian automatic speech recognition (ASR) model trained using the CTC loss function and can be utilized via the Hugging Face transformers library.

IndicConformer is a Conformer-based automatic speech recognition (ASR) model with a hybrid CTC-RNNT architecture, specifically designed for Gujarati speech transcription.

A Japanese automatic speech recognition model fine-tuned based on the microsoft/unispeech-sat-large model, trained using the Common Voice 7.0 Japanese dataset.

A Japanese automatic speech recognition model fine-tuned based on microsoft/wavlm-large, trained using the Common Voice 7.0 Japanese dataset

An English speech recognition model fine-tuned based on Microsoft's UniSpeech-SAT-Large model, supporting 16kHz sampled audio input.

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - ia dataset for automatic speech recognition in Interlingua.

A speech recognition model fine-tuned on the TIMIT dataset based on facebook/wav2vec2-large-lv60, supporting 16kHz sampled speech input.

Korean Automatic Speech Recognition (ASR) model based on Wav2Vec2 XLSR architecture, excelling on the Zeroth Korean dataset