Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

IBM updates Granite Speech with three open-weight models

AI summary

IBM released Granite Speech 5.0 2B and revised Granite Speech 5.0 Turbo CTC and Granite Speech 4.1 2B Plus, all under Apache 2.0 with native Transformers support. According to IBM, the new 2B model adds multilingual transcription and translation, language-ID prompting and keyword biasing for up to 2,000 terms, while Turbo CTC gains multilingual transcription and native punctuation; 4.1 2B Plus improves speaker attribution, timestamps and long-speech performance. IBM also reports a 5.06% average English WER for Granite Speech 5.0 2B and 19,870 RTFx for Turbo CTC, though these results are vendor-provided and the former ranking is described as unofficial.

In-depth insight

The release gives developers three open-licensed Granite Speech options for multilingual transcription, translation, high-throughput edge use and multi-speaker recordings, with reported improvements in accuracy, speed, timing and speaker attribution.

We're excited to share three updates to IBM's Granite Speech collection: a new speech-language model, granite-speech-5.0-2b, and revised versions of two models the community already uses, granite-speech-5.0-470m-turboctc and granite-speech-4.1-2b-plus. Together they cover the full range of enterprise speech work: transcription and translation with high accuracy, extremely fast transcription at the edge, and recordings where who spoke, and when, matter as much as what was said.

ModelStatusWhat's newBest for
granite-speech-5.0-2bNewMore accurate, noise- and reverb-robust automatic speech recognition (ASR), language-ID prompting, 2,000-term keyword biasing, better long-form translationHigh-accuracy multilingual transcription and translation
granite-speech-5.0-470m-turboctcUpdatedMultilingual, native punctuation and capitalization, and more robust to noise and reverbHigh-throughput and on-device transcription
granite-speech-4.1-2b-plusUpdatedImproved speaker attribution, timestamps, keyword biasing, and long-speech performanceMeetings, calls, and other multi-speaker recordings

Granite Speech 5.0 2B: more accurate, more robust, more control

granite-speech-5.0-2b is the successor to granite-speech-4.1-2b at the same parameter count. It transcribes English, French, German, Spanish, Portuguese, and Japanese, and translates to and from English in those languages, plus English to Italian and Mandarin. It was trained on 390,000 hours of public audio, plus synthetic data built for Japanese ASR, keyword biasing, and translation.

#IBM#Granite Speech 5.0 2B#Granite Speech 5.0 Turbo CTC#Granite Speech 4.1 2B Plus#Transformers#vLLM#llama.cpp#MLX Audio#Granite Guardian

Original · 4 min readRead the original
Group chat

No comments yet. Start the conversation.