Several advancements in the Whisper speech-to-text technology have been announced recently. Groq Whisper for Speech-to-Text (Audio Input) is now available. WhisperKit-0.9 has been released, featuring faster large v3 Turbo on Mac and iPhone, fast model load on TestFlight App, and memory reduction for large input handling. The Whisper Turbo model offers 8x speed compared to Whisper large, and a free Colab notebook is available for transcribing any audio file. Xinference v0.15.4 has introduced the whisper-large-v3-turbo audio model with enhanced tool call support, improved multimodal abilities, and customizable features. OpenAI's Whisper is an open-source, multilingual ASR system for transcription and translation without extra tuning, with the latest V3 Turbo version being 8x faster than large-v3 and compatible with cloud or local servers. Whisper-Turbo with Faster-Whisper is available on Hugging Face hub.
If anyone is interested in using Whisper-Turbo with Faster-Whisper, you can use this model from our Hugging Face hub: https://t.co/rgqJaKHZto
.@OpenAI's Whisper is an open-source, multilingual ASR system for transcription and translation without extra tuning The latest V3 Turbo version is 8x faster than large-v3, compatible with cloud or local servers Explore what makes Whisper so efficient👉 https://t.co/aqLI1Uhg0D
🔥 Thrilled to announce Xinference v0.15.4 release! 🎉 Introducing whisper-large-v3-turbo audio model 🎧, enhanced tool call support 🛠️, improved multimodal abilities 🌐, and customizable features! Download retries, chattts tweaks, and progress bars! 🚀 #Xinference #AI