# End-to-end Speech Processing

Speechless is a compact open-source text-to-semantic model (1 billion parameters) designed to directly convert audio into discrete semantic tokens without relying on traditional text-to-speech (TTS) models.

Speechless is a compact open-source text-to-semantic model (1 billion parameters) designed to directly convert audio into discrete semantic representation tokens without relying on traditional text-to-speech (TTS) models.

Audio classification model based on Wav2Vec 2.0 architecture, specifically designed for music genre recognition

An English automatic speech recognition (ASR) model fine-tuned based on microsoft/wavlm-base, trained on the english_ASR - CLEAN dataset with a word error rate (WER) of 0.0773.