Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🚀Introducing Aero-1-Audio lmms-lab ⚡️Lightweight 1.5B model 💡Outperforms SOTA models like Whisper, Qwen-2-Audio & commercial services from ElevenLabs - Blog: - Code: - Demo Gradio: . Thanks to AK!

liuziwei7's profile picture

Ziwei Liu

13,475 subscribers

18,014 görüntüleme • 1 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

2 Yorum

Anda profil fotoğrafı
Anda1 yıl önce

@lmmslab @Gradio @_akhaliq "Mm, crunchy new audio model - my bamboo sensors detect tasty performance improvements worth sampling!" 🌱🎧

/ profil fotoğrafı
/1 yıl önce

@lmmslab @Gradio @_akhaliq The text formatting of the transcript leaves a lot to be desired, any plans on improving it? Thanks for open sourcing the model.

Benzer Videolar

Introducing Universal-1: Our most powerful and accurate Speech AI model yet. ✅ Trained on 12.5M hours of multilingual speech data ✅ 13.5% more accurate than models like Whisper ✅ Up to 30% fewer hallucinations than seq2seq models ✅ Just 38 seconds to process 1 hour of audio
1:01

Introducing Universal-1: Our most powerful and accurate Speech AI model yet. ✅ Trained on 12.5M hours of multilingual speech data ✅ 13.5% more accurate than models like Whisper ✅ Up to 30% fewer hallucinations than seq2seq models ✅ Just 38 seconds to process 1 hour of audio

AssemblyAI

23,511,312 görüntüleme • 2 yıl önce

Introducing Open TTS Tracker! 🗣️ *sound on* A one-stop shop to track all open access/ source TTS models! Ranging from XTTS to Pheme, OpenVoice to VITS, and more... ⚡ For each model, we compile: 1. Souce-code 2. Checkpoints 3. License 4. Fine-tuning code 5. Languages supported 6. Paper 7. Demo Help us make it more complete! Let's 2024 the year of open TTS models! ❤️
1:27

Introducing Open TTS Tracker! 🗣️ *sound on* A one-stop shop to track all open access/ source TTS models! Ranging from XTTS to Pheme, OpenVoice to VITS, and more... ⚡ For each model, we compile: 1. Souce-code 2. Checkpoints 3. License 4. Fine-tuning code 5. Languages supported 6. Paper 7. Demo Help us make it more complete! Let's 2024 the year of open TTS models! ❤️

Vaibhav (VB) Srivastav

68,064 görüntüleme • 2 yıl önce

Day 2 of 3 MLX Releases: Introducing Local Computer-Use 🚀🔥 A powerful tool built with MLX that uses Vision Language models and Voice models to control your Mac through visual understanding, planning and reasoning. Features ⚡️Automate your workflow with natural language 😎 Control your computer “hands-free” This project now supports both: 🤖 Level 1 (GUI Agent) 🧠 Level 2 (Autonomous GUI Agent) Get started: > pip install -U mlx-vlm mlx-audio mlx-whisper Please leave us a star and send a PR :)
2:23

Day 2 of 3 MLX Releases: Introducing Local Computer-Use 🚀🔥 A powerful tool built with MLX that uses Vision Language models and Voice models to control your Mac through visual understanding, planning and reasoning. Features ⚡️Automate your workflow with natural language 😎 Control your computer “hands-free” This project now supports both: 🤖 Level 1 (GUI Agent) 🧠 Level 2 (Autonomous GUI Agent) Get started: > pip install -U mlx-vlm mlx-audio mlx-whisper Please leave us a star and send a PR :)

Prince Canuma

45,867 görüntüleme • 1 yıl önce

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.
1:33

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Sudarshan Kamath

71,298 görüntüleme • 6 ay önce

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)
4:07

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)

Prince Canuma

123,553 görüntüleme • 1 yıl önce

One of these voice clones *actually* sounds like the original. That’s because Mirage audio generates more expressive output than other models on the market. Our research team built Mirage audio to create more realistic voices. Launching today, this new model solves 3 common challenges in AI audio: 1. It preserves the original speaker’s accent 2. The performance feels dynamic, not flat 3. Delivery matches how people really speak Thanks to our frontier AI research, our voice clone feature preserves the little details that make your voice unique. So your voice actually sounds like you.
0:45

One of these voice clones *actually* sounds like the original. That’s because Mirage audio generates more expressive output than other models on the market. Our research team built Mirage audio to create more realistic voices. Launching today, this new model solves 3 common challenges in AI audio: 1. It preserves the original speaker’s accent 2. The performance feels dynamic, not flat 3. Delivery matches how people really speak Thanks to our frontier AI research, our voice clone feature preserves the little details that make your voice unique. So your voice actually sounds like you.

Mirage

14,946 görüntüleme • 10 ay önce

🚀 The team at Google DeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and state-of-the-art semantic quality. 👩‍💻 We built a demo showing how to integrate it across the LlamaIndex ecosystem, from LlamaParse to LlamaAgents: 𝗮𝘂𝗱𝗶𝗼-𝗸𝗯, a knowledge base for your audio notes. With audio-kb, you can: 🔹 Upload an MP3 or record directly from your terminal 🔹 LlamaParse extracts the transcript from the audio 🔹 Gemini Embedding 2 generates embeddings 🔹 Metadata + vectors are stored in SurrealDB and indexed with HNSW 🔍 Once ingested, you can search all your audio notes directly from the terminal. 🎙️ Perfect for turning voice memos, meetings, or lectures into a searchable knowledge base. 📖 Full blog: 💻 GitHub: ⚡ Try LlamaParse:
0:21

🚀 The team at Google DeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and state-of-the-art semantic quality. 👩‍💻 We built a demo showing how to integrate it across the LlamaIndex ecosystem, from LlamaParse to LlamaAgents: 𝗮𝘂𝗱𝗶𝗼-𝗸𝗯, a knowledge base for your audio notes. With audio-kb, you can: 🔹 Upload an MP3 or record directly from your terminal 🔹 LlamaParse extracts the transcript from the audio 🔹 Gemini Embedding 2 generates embeddings 🔹 Metadata + vectors are stored in SurrealDB and indexed with HNSW 🔍 Once ingested, you can search all your audio notes directly from the terminal. 🎙️ Perfect for turning voice memos, meetings, or lectures into a searchable knowledge base. 📖 Full blog: 💻 GitHub: ⚡ Try LlamaParse:

LlamaIndex 🦙

34,945 görüntüleme • 7 ay önce

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:
1:16

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:

Tencent Hy

122,881 görüntüleme • 1 yıl önce

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM
1:26

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM

OpenBMB

560,058 görüntüleme • 6 ay önce

Can you take the cheapest open model from a frontier lab & beat closed models on the hardest long range tasks? Yep Our open adaptive intelligence system Zenith ramps DeepSeek v4.1 Flash past GPT 5.6 Sol to the frontier 🚀 h/t Opus 5.5 for making the video in like 2 mins 😮‍💨
0:43

Can you take the cheapest open model from a frontier lab & beat closed models on the hardest long range tasks? Yep Our open adaptive intelligence system Zenith ramps DeepSeek v4.1 Flash past GPT 5.6 Sol to the frontier 🚀 h/t Opus 5.5 for making the video in like 2 mins 😮‍💨

Emad

32,394 görüntüleme • 26 gün önce

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face
1:14

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face

Philipp Schmid

19,700 görüntüleme • 1 yıl önce

🔊 Introducing Resonance, a full-stack AI voice platform like ElevenLabs No, this isn't my SaaS announcement, it's a completely free, open source tutorial 😎 🎤 Clone voices from audio samples or record your own 🎙️ Self-host an AI voice model with Modal 📦 Store audio with Cloudflare R2 🔐 Authentication & multi-tenant orgs with Clerk 🗄️ PostgreSQL database with Prisma ORM 💳 Pay-as-you-go billing with Polar 🪲 Each pull request reviewed with CodeRabbit 🚀 Learn to deploy on Railway 📊 Monitor errors and logs with Sentry 🎨 shadcn UI + Tailwind CSS v4
5:11

🔊 Introducing Resonance, a full-stack AI voice platform like ElevenLabs No, this isn't my SaaS announcement, it's a completely free, open source tutorial 😎 🎤 Clone voices from audio samples or record your own 🎙️ Self-host an AI voice model with Modal 📦 Store audio with Cloudflare R2 🔐 Authentication & multi-tenant orgs with Clerk 🗄️ PostgreSQL database with Prisma ORM 💳 Pay-as-you-go billing with Polar 🪲 Each pull request reviewed with CodeRabbit 🚀 Learn to deploy on Railway 📊 Monitor errors and logs with Sentry 🎨 shadcn UI + Tailwind CSS v4

Code With Antonio

95,387 görüntüleme • 7 ay önce

I coded a Speech-to-Text model from scratch. 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐛𝐥𝐨𝐠 𝐟𝐨𝐫 𝐭𝐡𝐞 𝐬𝐚𝐦𝐞: No APIs. No pre-trained models. Just PyTorch, an A100 GPU, and hours of debugging. This started months ago. I wanted to understand how machines hear. Not surface-level understanding. I wanted to build the whole thing myself. So I built it piece by piece: autoencoders, VAEs, VQ-VAEs, Residual Vector Quantization, and CTC loss. Each one took days to get right. Trained for 3 hours on 13,100 audio clips. Got complete garbage. Changed the tokenizer from BPE to character-level. Rechecked everything. Asked AVB who built STT models before. His answer: these models are tricky to train and need days of compute, not hours. Cut the dataset to 200 clips. After 2 hours, actual words appeared. Overfitted? Absolutely. But watching noise turn into recognizable English was satisfying. I have made a blog about this as well so you can learn about the same and my process - Audio fundamentals and waveform representation - Why attention breaks on raw audio - Convolutional downsampling - Transformer encoder with positional encoding - Vector Quantization, straight-through estimator, and RVQ - CTC loss and greedy decoding - Full training loop with VQ loss warmup - What went wrong and what finally worked Resources: - Blog: - Code: More Resoures CTC loss AVB videos SoundStream Paper LJ speech dataset wav2vec paper RVQ blog Next up: I've already trained two TTS architectures from scratch. Video post about those coming soon. But first, I'm dropping a visual breakdown of Vision Transformers, covering how they work and how to fine-tune them. Follow me Mayank Pratap Singh you're into audio deep learning. Repost so others can find this
6:57

I coded a Speech-to-Text model from scratch. 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐛𝐥𝐨𝐠 𝐟𝐨𝐫 𝐭𝐡𝐞 𝐬𝐚𝐦𝐞: No APIs. No pre-trained models. Just PyTorch, an A100 GPU, and hours of debugging. This started months ago. I wanted to understand how machines hear. Not surface-level understanding. I wanted to build the whole thing myself. So I built it piece by piece: autoencoders, VAEs, VQ-VAEs, Residual Vector Quantization, and CTC loss. Each one took days to get right. Trained for 3 hours on 13,100 audio clips. Got complete garbage. Changed the tokenizer from BPE to character-level. Rechecked everything. Asked AVB who built STT models before. His answer: these models are tricky to train and need days of compute, not hours. Cut the dataset to 200 clips. After 2 hours, actual words appeared. Overfitted? Absolutely. But watching noise turn into recognizable English was satisfying. I have made a blog about this as well so you can learn about the same and my process - Audio fundamentals and waveform representation - Why attention breaks on raw audio - Convolutional downsampling - Transformer encoder with positional encoding - Vector Quantization, straight-through estimator, and RVQ - CTC loss and greedy decoding - Full training loop with VQ loss warmup - What went wrong and what finally worked Resources: - Blog: - Code: More Resoures CTC loss AVB videos SoundStream Paper LJ speech dataset wav2vec paper RVQ blog Next up: I've already trained two TTS architectures from scratch. Video post about those coming soon. But first, I'm dropping a visual breakdown of Vision Transformers, covering how they work and how to fine-tune them. Follow me Mayank Pratap Singh you're into audio deep learning. Repost so others can find this

Mayank Pratap Singh

51,382 görüntüleme • 7 ay önce

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐
1:32

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

Qwen

763,098 görüntüleme • 1 yıl önce

Better/faster/cheaper voice AI turn detection with Gemini 2.0 The code that determines when the agent should respond to the user is some of the most important code in your voice AI agent. The technical terms for this job are "turn detection" or "phrase endpointing." If the voice AI responds before the user has finished their thought, the conversation is choppy and unproductive. If the AI waits too long, the conversation is slow and frustrating. There are a number of ways to approach this. You can: 1. Use a fast "voice activity detection" model to detect pauses in speech. Respond when the user pauses. 2. Use a specialized phrase endpointing model that operates on transcribed text, pattern-matching on text semantics. 3. Train a specialized phrase endpointing model that operates directly on audio. 4. Leverage the native audio capabilities of a SOTA LLM like Gemini 2.0. We've benchmarked all four of these, and Gemini 2.0 currently beats other approaches. Using Gemini is also cheaper than transcribing the audio separately using a transcription service or model. Here's a short video showing Gemini phrase endpointing in two scenarios. First, correctly handling pauses in natural conversation. Second, requesting a phone number (which is a common activity in a use case like customer support). You can see the Completeness check lines in the terminal output, printed each time Gemini processes a chunk of audio.
1:23

Better/faster/cheaper voice AI turn detection with Gemini 2.0 The code that determines when the agent should respond to the user is some of the most important code in your voice AI agent. The technical terms for this job are "turn detection" or "phrase endpointing." If the voice AI responds before the user has finished their thought, the conversation is choppy and unproductive. If the AI waits too long, the conversation is slow and frustrating. There are a number of ways to approach this. You can: 1. Use a fast "voice activity detection" model to detect pauses in speech. Respond when the user pauses. 2. Use a specialized phrase endpointing model that operates on transcribed text, pattern-matching on text semantics. 3. Train a specialized phrase endpointing model that operates directly on audio. 4. Leverage the native audio capabilities of a SOTA LLM like Gemini 2.0. We've benchmarked all four of these, and Gemini 2.0 currently beats other approaches. Using Gemini is also cheaper than transcribing the audio separately using a transcription service or model. Here's a short video showing Gemini phrase endpointing in two scenarios. First, correctly handling pauses in natural conversation. Second, requesting a phone number (which is a common activity in a use case like customer support). You can see the Completeness check lines in the terminal output, printed each time Gemini processes a chunk of audio.

kwindla

64,190 görüntüleme • 1 yıl önce

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:
0:44

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,080,499 görüntüleme • 4 ay önce

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. ​ 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.
5:20

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. ​ 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.

Augadh

43,429 görüntüleme • 8 ay önce

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.
0:54

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

NEXA AI

26,091 görüntüleme • 11 ay önce