# Low Word Error Rate

A multimodal speech recognition model optimized for Singapore English, fine-tuned based on Microsoft's Phi-4 multimodal instruction model, significantly improving recognition of Singapore English's unique phonetic features.

A speech recognition model fine-tuned from facebook/hubert-large-ls960-ft, trained on the LibriSpeech dataset

This model is a speech recognition model fine-tuned on the LibriSpeech dataset based on facebook/wav2vec2-base, achieving a word error rate of 0.3174 on the evaluation set.

This is a distilled version of Whisper Large V3 specifically optimized for French automatic speech recognition, achieving efficient inference through ctranslate2.

An Indian English accent speech recognition model fine-tuned based on OpenAI Whisper-large-v3-turbo, achieving a 7.99% word error rate on Indian English accent datasets

Lite-Whisper is a lightweight version of OpenAI Whisper compressed using LiteASR technology, maintaining high accuracy while reducing model size.

Whisper-large-v3-turbo fine-tuned model for Indian English accent speech recognition, with a word error rate of 4.39%

AudioX is a multilingual automatic speech recognition model developed by Jivi AI, specifically optimized for South Indian languages, supporting Tamil, Telugu, Kannada, and Malayalam.

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

Distil-Whisper is a knowledge-distilled version of OpenAI Whisper-Large-v3, achieving efficient speech recognition through large-scale pseudo-label training.

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.

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

A fine-tuned Traditional Chinese (Taiwan) automatic speech recognition model based on OpenAI Whisper-large-v3-turbo

Pathumma Whisper Large V3 is a Thai automatic speech recognition model based on the OpenAI Whisper architecture, supporting Thai and English speech transcription tasks.

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

A Malayalam automatic speech recognition model fine-tuned based on facebook/w2v-bert-2.0, trained on multiple Malayalam datasets and using a trigram language model trained with the KENLM library.

A distilled French version of Whisper-Large-V3, optimized for inference efficiency by reducing decoder layers while maintaining good performance

This model is a fine-tuned speech recognition model based on openai/whisper-large-v2, achieving a word error rate of 4.6858 on a specific domain dataset.

A speech recognition model fine-tuned based on facebook/wav2vec2-large-xlsr-53, focusing on phoneme recognition tasks

This model is a fine-tuned speech recognition model based on OpenAI's Whisper large on the Common Voice 14.0 Swahili (SW) dataset, achieving a word error rate (WER) of 25.13%.

This model is a fine-tuned speech recognition model based on openai/whisper-small on the Slovenian ASR dataset ARTUR 1.0, supporting Slovenian speech-to-text tasks.

A speech recognition model fine-tuned on the Turkish Common Voice dataset based on OpenAI Whisper-small

IndicWhisper is a cutting-edge speech recognition model optimized for Indian languages, excelling in various benchmark tests for Indian languages.

IndicWhisper is a cutting-edge speech recognition model optimized for Indian languages, excelling in various benchmarks for Indian languages.

This is a Thai automatic speech recognition model fine-tuned based on OpenAI's Whisper Large V3 model, achieving a 6.59% word error rate on the Common Voice 13 Thai test set.

A Whisper-based speech recognition model optimized for Haitian Creole, featuring high-accuracy speech-to-text conversion

Parakeet TDT 1.1B is an automatic speech recognition (ASR) model jointly developed by NVIDIA NeMo and Suno.ai, capable of transcribing speech into lowercase English letters.

An automatic speech recognition (ASR) model fine-tuned on the Common Voice 16.0 English dataset based on w2v-bert-2.0

This is a distilled version of the Whisper-Large-V3 French model, optimized for inference speed and memory usage by reducing the number of decoder layers while maintaining good performance.

A speech recognition model fine-tuned based on OpenAI Whisper-large-v3, specializing in Air Traffic Control (ATCO) scenarios with a word error rate of 17.04%

Turkish speech recognition model fine-tuned based on OpenAI Whisper-small, with a word error rate of 26.34%

An automatic speech recognition model based on the SpeechBrain framework, using a Conformer encoder and Transformer decoder, trained on the LibriSpeech dataset, supporting English speech recognition.

Korean speech recognition model based on the Whisper Small architecture, fine-tuned on multi-domain Korean datasets

An image caption generation model fine-tuned from microsoft/git-base, trained on Pokemon image dataset

Whisper-medium model fine-tuned on approximately 800 hours of diverse Estonian data, suitable for general speech recognition scenarios

A Telugu automatic speech recognition model fine-tuned based on OpenAI Whisper-large-v2, trained on multiple public Telugu datasets

A Telugu automatic speech recognition (ASR) model fine-tuned based on OpenAI Whisper-base, trained on multiple public Telugu datasets

This model is a speech recognition model fine-tuned on the Common Voice 11.0 Slovenian dataset based on OpenAI's Whisper Large-V2 model, with a word error rate of 13.83%.

A Kannada automatic speech recognition model fine-tuned based on openai/whisper-tiny, trained on multiple public Kannada ASR corpora

This is a Hindi automatic speech recognition (ASR) model fine-tuned based on OpenAI Whisper Large V2, trained on the Common Voice 11.0 dataset with a word error rate (WER) of 10.05%.