🚨 🔔 Paper alert in Efficient Streaming ASR 🔔🚨 I'm super excited to release our paper “XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models” abs: https://t.co/C2egeieWAd [1/n]

The LFM2 Tech Report is now live on arXiv! We share everything from our novel hardware-in-the-loop architecture design, pre-training, and knowledge distillation, to the post-training recipe for small models. > 🤗LFM2 class of models has over 3.3M downloads > ⚛️LFM2 nanos from

It's great to have FocalCodec in SpeechBrain! 📄 Paper: https://t.co/Wy8y0NvGxJ 💻 Training Code (SpeechBrain): https://t.co/rDDgkaXwIc 🎧 Pretrained Model: https://t.co/i6poMR2EDM 🔊 Demo Samples: https://t.co/gujaTUHE5q As always, true open-source, not just open weights!

One of the first books where I see a QR code that enhances the reading experience! 🫶🏽 “Salvo mi corazón, todo está bien”

We are back to the age of research! Very wise words! @ilyasut

The @ilyasut episode 0:00:00 – Explaining model jaggedness 0:09:39 - Emotions and value functions 0:18:49 – What are we scaling? 0:25:13 – Why humans generalize better than models 0:35:45 – Straight-shotting superintelligence 0:46:47 – SSI’s model will learn from deployment

Need to customize vLLM? Don't fork it. 🔌 vLLM's plugin system lets you inject surgical modifications without maintaining a fork or monkey-patching entire modules. Blog by Dhruvil Bhatt from AWS SageMaker 👇 Why plugins > forks: • vLLM releases every 2 weeks with 100s of PRs

We’re open-sourcing a set of high quality speculator models for Llamas, Qwens, and gpt-oss on Hugging Face. In real workloads, you can expect 1.5 to 2.5x speedups and sometimes more than 4x. Here’s how this fits into the bigger story for speculative decoding. A thread 🧵:

Making CUDA+TORCH+UNSLOTH+vLLM work at the same time it’s kinda… 🫠

Zürich @vllm_project meetup is live! Watch our live stream here on X or on YouTube: https://t.co/FfpHd36gfb

@Pablogomez3 @vllm_project 🚀🚀🚀 Join us live from Zürich on YouTube:

Let’s do ittttt! First @vllm_project meetup in Europe! @RedHat_AI

We are closing the registration today - grab your spot now!

We’re hosting the first official vLLM Meetup in Europe with @IBM & @MistralAI on Nov 6 in Zurich 🇨🇭 Join vLLM core committers to dive into inference, quantization, Mistral + vLLM, hybrid models & distributed inference with @_llm_d_. Register 👉 https://t.co/kUeGXtv1kY Agenda 👇

👋Say Hi to MiMo-Audio! Our BREAKTHROUGH in general-purpose audio intelligence. 🎯 Scaling pretraining to 100M+ hours leads to EMERGENCE of few-shot generalization across diverse audio tasks! 🔥 Post-trained MiMo-Audio-7B-Instruct: • crushes benchmarks: SOTA on MMSU, MMAU,

Siempre el mismo cuento @AABenedetti 🙄: “es que Trump está mal informado”, “es que la ONU hizo mal las cuentas”, “es que @berniemoreno dice en EEUU lo que no es”. Puras excusas. ¿Ahora también dirá que Coronel miente cuando Ud. estuvo en esa entrevista? https://t.co/Mp4pvoHbrl

Ready for Indiaaaaaaaa 🇮🇳 🫓

🎙️ Come and work with us, we are offering a paid Research Internship position in Large-scale data processing for SOTA Speech Models. 🇨🇭 We are young and nice team located in Zurich. 📃 Possibility to publish results of the internship. https://t.co/fEutbwRAXz

🎙️ Come and work with us, we are offering a paid Research Internship position in Text-to-speech. 🇨🇭 We are young and nice team located in Zurich. 📃 Possibility to publish results of the internship. https://t.co/o13bxkY4kc

🎙️ Come and work with us, we offer a paid Research Internship position in developing an evaluation framework for Text-to-speech systems. 🇨🇭 We are young and nice team located in Zurich. 📃 Possibility to publish results of the internship. https://t.co/z4Yd1RLVDp

🎙️ Come and work with us, we offer a paid Research Internship position in building a universal phonetizer system for next-generation Voice AI systems! 🇨🇭 We are young and nice team located in Zurich. 📃 Possibility to publish results of the internship. https://t.co/ff3nl1qdvl