Moonshine Tiny is a lightweight Vietnamese automatic speech recognition model developed by Moonshine AI (formerly Useful Sensors). It has only 27M parameters and is specifically designed for resource-constrained platforms. It performs excellently on the Fleurs and Common Voice 17 datasets.

Audio ProcessingTransformersOther

Hindi automatic speech recognition model based on Wav2Vec2 architecture, developed by AI4Bharat

Audio ProcessingTransformersOther

AudioX is a multilingual automatic speech recognition model developed by Jivi AI, optimized for Indian languages, supporting Hindi, Gujarati, and Marathi.

Audio ProcessingSafetensorsOther

This is a large-scale automatic speech recognition model trained on a 25,000-hour English speech dataset. It uses the Conformer architecture and is contributed by Samsung AI Cambridge Center. The model has 480 million parameters and performs well on multiple test sets, with a WER of 6.8% on the validation set and 7.5% on the test set.

Audio ProcessingSpeechbrainEnglish

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

Audio ProcessingSafetensorsOther

A Latvian automatic speech recognition model fine-tuned based on whisper-large-v3, trained by AiLab.lv, supporting Latvian speech-to-text tasks.

Audio ProcessingSafetensorsOther

A speech emotion recognition model fine-tuned based on airesearch/wav2vec2-large-xlsr-53-th, achieving 85.79% accuracy on the evaluation set

Audio ProcessingTransformers

A Thai speech emotion recognition model fine-tuned from airesearch/wav2vec2-large-xlsr-53-th, supporting anger, happiness, and calm emotion classification

Audio ProcessingTransformers

Fine-tuned based on the OpenAI Whisper Medium EN model, specifically optimized for speech recognition of air traffic control communications, with an 84% reduction in word error rate

Audio ProcessingSafetensorsEnglish

A speech recognition model fine-tuned based on OpenAI Whisper Medium EN, specifically optimized for Air Traffic Control (ATC) communication scenarios, achieving an 84% reduction in Word Error Rate (WER)

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%

Audio ProcessingTransformers

Hindi automatic speech recognition (ASR) model based on Wav2Vec2 architecture, developed by AI4Bharat

Audio ProcessingTransformersOther

A speech recognition model fine-tuned on the UWB-ATCC Air Traffic Control Communication dataset based on the facebook/wav2vec2-large-960h-lv60-self model

Audio ProcessingTransformersEnglish

An air traffic control speech recognition model fine-tuned on wav2vec2-xls-r-300m, supporting English

Audio ProcessingTransformersEnglish

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the ATCOSIM corpus, specifically designed for automatic speech recognition tasks in air traffic control communications.

Audio ProcessingTransformersEnglish

An automatic speech recognition model based on wav2vec2-large-xlsr-53, specifically optimized for StepMania game audio, fine-tuned on the GARY109/AI_LIGHT_DANCE dataset

Audio ProcessingTransformers

An automatic speech recognition model fine-tuned based on wav2vec2-large-xlsr-53, trained on the GARY109/AI_LIGHT_DANCE dataset

Audio ProcessingTransformers

This model is an automatic speech recognition (ASR) model fine-tuned on the GARY109/AI_LIGHT_DANCE - ONSET-STEPMANIA2 dataset based on wav2vec2-large-xlsr-53.

Audio ProcessingTransformers

This model is an automatic speech recognition (ASR) model based on the wav2vec2-large-xlsr-53 architecture, fine-tuned on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING2 dataset, primarily used for singing voice recognition tasks.

Audio ProcessingTransformers

Automatic speech recognition model based on wav2vec2-large-xlsr-53, fine-tuned on the GARY109/AI_LIGHT_DANCE dataset

Audio ProcessingTransformers