# LibriSpeech fine-tuning

A text-to-speech model fine-tuned on the German LibriSpeech dataset based on Microsoft's SpeechT5 model

Data2Vec is a general self-supervised learning framework applicable to speech, vision, and language tasks. This large audio model is pre-trained and fine-tuned on 960 hours of LibriSpeech data, specifically optimized for automatic speech recognition tasks.

Automatic speech recognition model fine-tuned on the LIBRISPEECH_ASR - CLEAN dataset based on microsoft/wavlm-large

This model is a speech recognition model fine-tuned on the LibriSpeech 100-hour dataset based on facebook/wav2vec2-large-lv60, achieving a low word error rate.