# High Accuracy Transcription

This model is a Japanese automatic speech recognition (ASR) model based on the FastConformer architecture, developed by NVIDIA and converted to MLX format.

NVIDIA FastConformer-Hybrid Large is a Russian automatic speech recognition model based on the FastConformer architecture, supporting CTC and RNN-T decoders.

A small speech recognition model based on the OpenAI Whisper architecture, focused on English speech-to-text tasks.

An Albanian-optimized speech recognition model based on OpenAI Whisper Large v3 Turbo, supporting standard Albanian and Gheg dialect

This model is a voice cloning model fine-tuned based on openai/whisper-large-v3, primarily used for speech recognition tasks, achieving a word error rate of 15.3572 on the evaluation set.

Whisper is a multilingual automatic speech recognition (ASR) system that supports speech-to-text tasks in multiple languages.

A Chinese speech recognition model fine-tuned and optimized based on whisper-large-v3, showing significant performance improvements in multiple Chinese speech benchmarks

This is a hybrid model for Persian Automatic Speech Recognition (ASR), combining transducer and CTC decoder losses, optimized based on the FastConformer architecture.

A fine-tuned German speech recognition model based on Whisper Large v3, optimized for German speech processing and recognition

ONNX format conversion of Facebook's wav2vec2-base-960h model, designed for Transformers.js, supporting browser-side speech recognition

Large-scale speech recognition model based on the wav2vec 2.0 architecture, supporting English speech-to-text conversion

This is the CTranslate2 converted version of the whisper-large-v2-mix-jp model, suitable for Japanese speech recognition tasks

A fine-tuned speech recognition model based on facebook/wav2vec2-xls-r-300m, trained on the ASCEND dataset

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base-960h on an unknown dataset, primarily used for automatic speech recognition tasks.

This is a Gujarati speech recognition model based on the Wav2Vec2 architecture, capable of directly converting Gujarati speech into text.

Automatic Speech Recognition (ASR) model trained on the LibriSpeech dataset

A Kannada speech recognition model based on the Wav2Vec2 architecture, capable of directly converting Kannada speech into text.

This is a Urdu speech recognition model based on the Wav2Vec2 architecture, capable of converting Urdu speech into text.

This model is a speech recognition model fine-tuned on the WSJ0 dataset based on facebook/wav2vec2-large-lv60, achieving a word error rate of 0.0343 on the evaluation set.