Hugging Face's logo

Posts, articles, and discussions

Making automatic speech recognition work on large files with Wav2Vec2 in 🤗 Transformers

By Narsil February 1, 2022

Boost Wav2Vec2 with n-gram LM in 🤗 Transformers

By patrickvonplaten January 12, 2022

Perceiver IO: a scalable, fully-attentional model that works on any modality

By nielsr December 15, 2021

Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers

By patrickvonplaten November 15, 2021

Fine-Tune Wav2Vec2 for English ASR with 🤗 Transformers

By patrickvonplaten March 12, 2021

Community Events

Apr 13, 2022 Accelerate BERT Inference with Knowledge Distillation & AWS Inferentia Accelerate BERT Inference with knowledge distillation & compiling using Hugging Face Transformers, Amazon SageMaker & AWS Inferentia. Apr 5, 2022 Computer Vision Study Group Paper Reading Session on "How Do Vision Transformers Work?" Discussion on paper "How Do Vision Transformers Work?". Mar 14 to Mar 31, 2022 NLP in Spanish Hackathon Largest Hackathon ever of NLP in Spanish. Mar 22, 2022 Chasing the wrong benchmarks in Machine Learning, How it will fail in production Niels Reimers will present his view on chasing wrong benchmarks in ML and how they will fail in production. Feb 16, 2022 NLP with TF Keras and HF Transformers with Merve Noyan Learn about how NLP can be done with TensorFlow and Transformers. Jan 24 to Feb 7, 2022 Robust Speech Recognition Challenge Community event in which robust speech recognition systems in many languages are created. Feb 3, 2022 Hub Featureton Would you like to know all the things you can do with the Hub? This event is for you! During the webinar, we'll go through some amazing features the Hugging Face team has been working on. Jan 21, 2022 XLS-R, Large-Scale Cross-lingual Speech Representation Learning on 128 Languages Changan Wang, from Meta AI Research, is one of the authors of the XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec. Jan 21, 2022 The Common Voice Dataset Gabriel Habayeb, from Mozilla Common Voice, will join us to speak about the Common Voice Dataset. Jan 19, 2022 ML for Audio Study Group - ML4Audio - pyctcdecode, A simple and fast speech-to-text prediction decoding algorithm Watch a presentation about pyctcdecode, a fast and feature-rich CTC beam search decoder for speech recognition.