This work has been accepted at Interspeech 2026!
Come visit the @argmax booth in Sydney this September to learn about our other advancements in speech and speaker recognition.
argmax
@argmax
Frontier Models On Device
- Argmax now runs on Google Tensor TPU, the first-ever SDK to harness this edge inference accelerator! Tensor TPU enabled us to deploy billion-scale transformers reliably on Pixel phones without impacting battery life or resource contention with traditional workloads.
00:00Argmax TPU Engine is built with @googledevs LiteRT and Google Tensor ML SDK. Learn more about Google LiteRT here: developers.googleblog.com/building-real-…Q: How do I add support for Tensor TPUs in my app? A: The next release of Argmax Pro SDK Kotlin will generate TPU-optimized Parakeet models. Q: What are the code changes I need to make? A: Installation and Google Play integration remain the same as before. No code changes - Argmax OSS (formerly WhisperKit) just crossed 10M monthly on @huggingface! - First ever Apple Silicon-only model to cross 10M - Usage grew 10x in ~100 days - Free, MIT Open-source and pure Swift
We are thrilled that WhisperKit reached 1 million monthly on @huggingface! - First ever Apple Silicon-only model to reach 1M - Usage grew 10x in 2025 - Free, MIT open-source and pure-SwiftOn-device is becoming the default way to deploy commercial-grade speech recognition. Join the movement: - Google just published a blog post on the real-world commercial adoption of their new on-device inference runtime, LiteRT! Heidi Health and Argmax are highlighted as the prime example of running medical transcription on Android devices, improving reliability, speed, and privacy
- WhisperKit is now Argmax OSS! As part of our continued commitment to open-source, we are releasing part of Argmax Pro SDK, extending WhisperKit beyond speech-to-text. Argmax OSS now includes: - SpeakerKit: Add speaker info to your transcripts with the fastest implementation of
Replying to @argmaxSpeakerKit We launched SpeakerKit last year as part of Argmax Pro SDK. We published a research paper to demonstrate that SpeakerKit is the fastest Pyannote implementation, with verified accuracy parity across 13 datasets: isca-archive.org/interspeech_20… SpeakerKit Pro has reached
WhisperKit WhisperKit is now 26 months old, and it recently crossed 6,000,000 monthly downloads: huggingface.co/argmaxinc/whis… It remains the most reliable implementation of Whisper on Apple Silicon, running Large v3 Turbo in real-time on iOS used by developers and Enterprises inIntroducing WhisperKit takeargmax.com/blog/whisperkit
00:00
