wav2vec2-large-robust-ft-libri-960h EU AI Act Compliance Profile

Wav2Vec2-Large-Robust finetuned on Librispeech

Facebook's Wav2Vec2.

This model is a fine-tuned version of the wav2vec2-large-robust model. It has been pretrained on:

• Libri-Light: open-source audio books from the LibriVox project; clean, read-out audio data
• CommonVoice: crowd-source collected audio data; read-out text snippets
• Switchboard: telephone speech corpus; noisy telephone data
• Fisher: conversational telephone speech; noisy telephone data

and subsequently been finetuned on 960 hours of

• Librispeech: open-source read-out audio data.

When using the model make sure that your speech input is also sampled at 16Khz.

Paper Robust Wav2Vec2

Authors: Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli

Abstract Self-supervised learning of speech representations has been a very active research area but most work is focused on a single domain such as read audio books for which there exist large quantities of labeled and unlabeled data. In this paper, we explore more general setups where the domain of the unlabeled data for pre-training data differs from the domain of the labeled data for fine-tuning, which in turn may differ from the test data domain. Our experiments show that using target domain data during pre-training leads to large performance improvements across a variety of setups. On a large-scale competitive setup, we show that pre-training on unlabeled in-domain data reduces the gap between models trained on in-doma

Your obligations as a wav2vec2-large-robust-ft-libri-960h deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library