TLDRocket
Sign in
Latest Google unveils TorchTPU in a push to break Nvidia’s stranglehold on AI... — SiliconANGLE OpenAI acquires Orchestra Bio to bring AI agents into drug development — SiliconANGLE Elon Musk says Tesla-SpaceX merger being considered — BBC News Open-Ended Exploration for Decision Support: QD-Rec for Improving Reco... — Sakana AI [Event Report] Sakana AI Engineer Open House 2026 — Sakana AI The tech helping crack decades-old cold cases — BBC News DeepSeek open-sources DeepInfer, the inference framework behind its pr... — SiliconANGLE Anthropic Does Not Understand Why Its Draft Bill Was Unacceptable and... — Zvi (Don't Worry About the Vase)

The AI intelligence platform

Every AI story that matters — and the intelligence behind it.

TLDRocket reads all relevant sources, removes duplicate coverage, and publishes a short neutral summary of every story, linking back to the original. Free, no spam, unsubscribe anytime.

Add to Slack

Every story also updates live profiles event timelines weekly rankings the AI Market Index

Wednesday, 12 January 2022

Boosting Wav2Vec2 with n-grams in 🤗 Transformers

Hugging Face 4 years ago 50

The Hugging Face Transformers library now supports integrating n-gram language models with Wav2Vec2 speech recognition through the pyctcdecode library. The integration allows users to combine a fine-tuned Wav2Vec2 checkpoint with a language model using the Wav2Vec2ProcessorWithLM class, which applies beam search across a matrix of character probabilities weighted by language model predictions. This approach significantly reduces spelling errors in transcriptions: a test case corrected "christmaus" to "christmas" and "simalyis" to "similes," though ambiguities between valid words like "rose" versus "roast" persist based on acoustic probability weighting.

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.