Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which... was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...show more

kwindla

14,713 subscribers

42,219 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses three NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,403 views • 6 months ago

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

LiveKit

126,860 views • 1 year ago

Voice AI turn taking is a solved problem. The single most common complaint about voice AI, today, is that agents interrupt too often. But the voice agents I build for myself now respond quickly and interrupt me less often than the people I talk to every day. (I actually measured this.) Mark Backman made a Pipecat AI PR two weeks ago that was the last piece of the puzzle for turn taking so good that I no longer ever think about it. The approach combines three layers of processing: 1. Voice activity detection, with a short (200ms) trigger. 2. A native audio turn detection model that's small, fast, and runs on CPU. This model captures audio nuances like inflection and filler sounds that don't get transcribed. 3. A prompt mixin for the conversation LLM that decides turn completion based on conversation context. None of these are new. We've been using VAD for a long time. We trained the first version of the Pipecat Smart Turn native audio model in December 2024. And we've been experimenting with prompt-based large model turn detection (sometimes called "selective refusal") for more than a year. Now, the Smart Turn model and the SOTA LLMs we're using in voice agents have both gotten so good that using them together feels like we've finally "solved" turn detection. Mark also figured out how to elegantly apply a "single-token tagging" technique to this problem. We sometimes use single-token tagging in place of tool calling, when we need a near-zero latency programmatic trigger. Mark's Pipecat mixin defines three single-token characters and prompts the LLM to output exactly one of them at the beginning of every response. - ✓ means the agent should respond normally (immediately) - ○ is a "short incomplete" - the agent should wait 5 seconds - ◐ is a "long incomplete" - the agent should wait 10 seconds The wait times, and the details of the prompt, are configurable, of course. Watch the video to see me talk to an agent that handles all my various pauses and inflections, plus phrases like "let me think," pretty much the way a person would handle them, in terms of response latency. Also, in the second half of the video, I ask the agent to adjust its response pattern because I'm going to tell it a phone number. This kind of "in-context" adjustment of response wait times is really useful. The LLM in the video is GTP-4.1. We've tested the prompt and single-token adherance with GPT-4.1, Gemini 2.5 Flash, Anthropic Claude Sonnet 4.5, and AWS Nova 2 Pro. Note that older models in all these families (and, in general, smaller open weights models) aren't able to reliably output these single-token tags. But the new models we're using these days are pretty amazing.

Voice AI turn taking is a solved problem. The single most common complaint about voice AI, today, is that agents interrupt too often. But the voice agents I build for myself now respond quickly and interrupt me less often than the people I talk to every day. (I actually measured this.) Mark Backman made a Pipecat AI PR two weeks ago that was the last piece of the puzzle for turn taking so good that I no longer ever think about it. The approach combines three layers of processing: 1. Voice activity detection, with a short (200ms) trigger. 2. A native audio turn detection model that's small, fast, and runs on CPU. This model captures audio nuances like inflection and filler sounds that don't get transcribed. 3. A prompt mixin for the conversation LLM that decides turn completion based on conversation context. None of these are new. We've been using VAD for a long time. We trained the first version of the Pipecat Smart Turn native audio model in December 2024. And we've been experimenting with prompt-based large model turn detection (sometimes called "selective refusal") for more than a year. Now, the Smart Turn model and the SOTA LLMs we're using in voice agents have both gotten so good that using them together feels like we've finally "solved" turn detection. Mark also figured out how to elegantly apply a "single-token tagging" technique to this problem. We sometimes use single-token tagging in place of tool calling, when we need a near-zero latency programmatic trigger. Mark's Pipecat mixin defines three single-token characters and prompts the LLM to output exactly one of them at the beginning of every response. - ✓ means the agent should respond normally (immediately) - ○ is a "short incomplete" - the agent should wait 5 seconds - ◐ is a "long incomplete" - the agent should wait 10 seconds The wait times, and the details of the prompt, are configurable, of course. Watch the video to see me talk to an agent that handles all my various pauses and inflections, plus phrases like "let me think," pretty much the way a person would handle them, in terms of response latency. Also, in the second half of the video, I ask the agent to adjust its response pattern because I'm going to tell it a phone number. This kind of "in-context" adjustment of response wait times is really useful. The LLM in the video is GTP-4.1. We've tested the prompt and single-token adherance with GPT-4.1, Gemini 2.5 Flash, Anthropic Claude Sonnet 4.5, and AWS Nova 2 Pro. Note that older models in all these families (and, in general, smaller open weights models) aren't able to reliably output these single-token tags. But the new models we're using these days are pretty amazing.

kwindla

26,879 views • 5 months ago

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.

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

64,184 views • 1 year ago

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.

Santiago

44,783 views • 1 year ago

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

kwindla

40,319 views • 1 month ago

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Charly Wargnier

565,090 views • 5 months ago

This robot assistant from the NVIDIA CES Keynote on Monday is going viral. Nader Khalil🍊 explains all the hottest emerging AI trends in one demo: AI applications in 2026 will be multi-model, multi-modal, hybrid cloud/local, use open source models as well as proprietary models, control robots and embedded devices in the physical world, and have voice interfaces. (And the demo had a cute robot *and* a cute dog. Gold.) The demo was built with Pipecat AI. NVIDIA posted a really nice technical walk-through and complete code. The Reachy Mini robot from Hugging Face is open source hardware. (You can order it now, I have one!). You can run the assistant locally on your own hardware, in the cloud, or both.

This robot assistant from the NVIDIA CES Keynote on Monday is going viral. Nader Khalil🍊 explains all the hottest emerging AI trends in one demo: AI applications in 2026 will be multi-model, multi-modal, hybrid cloud/local, use open source models as well as proprietary models, control robots and embedded devices in the physical world, and have voice interfaces. (And the demo had a cute robot and a cute dog. Gold.) The demo was built with Pipecat AI. NVIDIA posted a really nice technical walk-through and complete code. The Reachy Mini robot from Hugging Face is open source hardware. (You can order it now, I have one!). You can run the assistant locally on your own hardware, in the cloud, or both.

kwindla

48,964 views • 6 months ago

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

Ilir Aliu - eu/acc

17,353 views • 10 months ago

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

girish

453,691 views • 1 month ago

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗

Vaibhav (VB) Srivastav

156,386 views • 2 years ago

So helped me to unlock the voice now it works! It's trained on my Lex Fridman podcast It's 99% perfect but the training data apparently still has some Lex "hummm" sounds in it that sometimes show up I think they call this "crosstalk" and it's hard to remove with AI so I think there's no other choice than to listen to the 1 hour of training data and remove those bits and re-train But then we have a good AI model to turn my book MAKE into an audio book without having to read it for hours/days/weeks

So helped me to unlock the voice now it works! It's trained on my Lex Fridman podcast It's 99% perfect but the training data apparently still has some Lex "hummm" sounds in it that sometimes show up I think they call this "crosstalk" and it's hard to remove with AI so I think there's no other choice than to listen to the 1 hour of training data and remove those bits and re-train But then we have a good AI model to turn my book MAKE into an audio book without having to read it for hours/days/weeks

@levelsio

169,759 views • 1 year ago

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

Jun Gao

103,890 views • 1 month ago

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,821 views • 2 years ago

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,128 views • 11 months ago

Excited to introduce Fish Speech 1.4 - now open-source and more powerful than ever! 🎉 Our mission is to make cutting-edge voice tech accessible to everyone. What's new: - Trained on 700k hours of multilingual data (up from 200k) - Now supports 8 languages: English, Chinese, German, Japanese, French, Spanish, Korean, and Arabic - Fully open-source, empowering developers and researchers worldwide Key features: - Lightning-fast TTS with ultra-low latency - Instant voice cloning - Self-host or use our cloud service - Simple, flat-rate pricing Try it out: - Playground: - GitHub: - HuggingFace Model: - Demo: - Product Hunt: We can't wait to see what you'll create with Fish Audio. Happy voice building! 🎧🐠

Excited to introduce Fish Speech 1.4 - now open-source and more powerful than ever! 🎉 Our mission is to make cutting-edge voice tech accessible to everyone. What's new: - Trained on 700k hours of multilingual data (up from 200k) - Now supports 8 languages: English, Chinese, German, Japanese, French, Spanish, Korean, and Arabic - Fully open-source, empowering developers and researchers worldwide Key features: - Lightning-fast TTS with ultra-low latency - Instant voice cloning - Self-host or use our cloud service - Simple, flat-rate pricing Try it out: - Playground: - GitHub: - HuggingFace Model: - Demo: - Product Hunt: We can't wait to see what you'll create with Fish Audio. Happy voice building! 🎧🐠

Fish Audio

149,977 views • 1 year ago

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Rohan Paul

15,672 views • 3 months ago

Tune Studio is an end-to-end platform for developing applications using Large Language Models. So far, I haven't seen any other platform like this one. You can do everything here: 1. You can curate your data. 2. Use the playground to play with different models and try your ideas. 3. Fine-tune an open-source model on your data. 4. Deploy the model when you are done. This is awesome for anyone building generative AI applications. You can use Tune Studio to work with any of the open-source models out there. They were one of the few companies to host Llama 2 and Llama 3 before anyone else. Here is a link to check it out: One of their main selling points is that Tune Studio scales! You don't have to worry about serving your model to lots of users. They also have built-in user management, authentication, on-prem support, user context management, and pretty much everything you need to build generative AI applications. Thanks to the Tune team for collaborating with me on this post. We are living through the best years of development tools for AI developers. The field is unstoppable.

Tune Studio is an end-to-end platform for developing applications using Large Language Models. So far, I haven't seen any other platform like this one. You can do everything here: 1. You can curate your data. 2. Use the playground to play with different models and try your ideas. 3. Fine-tune an open-source model on your data. 4. Deploy the model when you are done. This is awesome for anyone building generative AI applications. You can use Tune Studio to work with any of the open-source models out there. They were one of the few companies to host Llama 2 and Llama 3 before anyone else. Here is a link to check it out: One of their main selling points is that Tune Studio scales! You don't have to worry about serving your model to lots of users. They also have built-in user management, authentication, on-prem support, user context management, and pretty much everything you need to build generative AI applications. Thanks to the Tune team for collaborating with me on this post. We are living through the best years of development tools for AI developers. The field is unstoppable.

Santiago

39,101 views • 2 years ago