Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

OpenAI's S2S preview is polished but it still thinks in steps. Speech → text → model → text → speech. That's not how humans converse. Introducing Hydra. A native speech-to-speech model that doesn't wait for turn-taking, doesn't flatten emotion into text, and doesn't break when you interrupt it mid-sentence.... show more

Sudarshan Kamath

21,775 subscribers

328,852 Aufrufe • vor 4 Monaten •via X (Twitter)

Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 Aufrufe • vor 3 Jahren

.Andrew Doyle: “If you look at all the various definitions of hate speech across European statute books, none of them agree. No one knows what it is really.” The concept of hate speech is being used to erode free speech across Europe, argues comedian and writer Andrew Doyle, author of “Free Speech and Why It Matters.” “No one can define hate speech. No one knows what it means. And [yes] human beings hate. That's an emotion that has developed in us over many, many years. You can't wish away a human emotion with the stroke of a pen. You may as well try and legislate against envy. It doesn't make sense,” he says. “People [are] trying to eliminate free speech or draw their own exceptions or carve out exceptions. That's why the First Amendment—even though it's a great protection—is not invulnerable to attack or modification or misinterpretation. All of that can still happen.” Free speech, he says, is never something that’s won, it’s something that needs to be fought for always.

.Andrew Doyle: “If you look at all the various definitions of hate speech across European statute books, none of them agree. No one knows what it is really.” The concept of hate speech is being used to erode free speech across Europe, argues comedian and writer Andrew Doyle, author of “Free Speech and Why It Matters.” “No one can define hate speech. No one knows what it means. And [yes] human beings hate. That's an emotion that has developed in us over many, many years. You can't wish away a human emotion with the stroke of a pen. You may as well try and legislate against envy. It doesn't make sense,” he says. “People [are] trying to eliminate free speech or draw their own exceptions or carve out exceptions. That's why the First Amendment—even though it's a great protection—is not invulnerable to attack or modification or misinterpretation. All of that can still happen.” Free speech, he says, is never something that’s won, it’s something that needs to be fought for always.

Jan Jekielek

43,084 Aufrufe • vor 6 Monaten

💥Bill Maher SCHOOLS Canadian Comedian Tom Green on why Canada *DOESN'T* have free speech like America🇺🇸 GREEN: "We have freedom of speech … There are hate speech laws in Canada — so there are things you can't say ... Who would want to say that sh*t anyways?" MAHER: "That's not what free speech means … You don’t know what free speech is." "The Supreme Court ruled in our country that the Nazis could march in Skokie, Illinois — which they were marching in because it is a community of a lot of Holocaust survivors ... That is what free speech is about."

💥Bill Maher SCHOOLS Canadian Comedian Tom Green on why Canada DOESN'T have free speech like America🇺🇸 GREEN: "We have freedom of speech … There are hate speech laws in Canada — so there are things you can't say ... Who would want to say that sh*t anyways?" MAHER: "That's not what free speech means … You don’t know what free speech is." "The Supreme Court ruled in our country that the Nazis could march in Skokie, Illinois — which they were marching in because it is a community of a lot of Holocaust survivors ... That is what free speech is about."

Jason Cohen 🇺🇸

1,442,608 Aufrufe • vor 9 Monaten

SANDERS: Is healthcare a human right? RFK JR: In the way that free speech is a human right? ... Free speech doesn't cost anything. But in healthcare, if you smoke cigarettes for 20 years and you get cancer, you are now taking from the pool. Are you guaranteed the same right?

SANDERS: Is healthcare a human right? RFK JR: In the way that free speech is a human right? ... Free speech doesn't cost anything. But in healthcare, if you smoke cigarettes for 20 years and you get cancer, you are now taking from the pool. Are you guaranteed the same right?

Daily Wire

416,390 Aufrufe • vor 1 Jahr

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀

Lucas Newman

22,962 Aufrufe • vor 1 Jahr

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Aoden Teo

5,155,375 Aufrufe • vor 1 Monat

Along with text, images, video and code, Gemini is able to process raw audio signal end-to-end. 🔊 It can listen to and understand speech, making it not only useful for transcription but a model that has a much more nuanced perception of its environment. ↓

Along with text, images, video and code, Gemini is able to process raw audio signal end-to-end. 🔊 It can listen to and understand speech, making it not only useful for transcription but a model that has a much more nuanced perception of its environment. ↓

Google DeepMind

140,169 Aufrufe • vor 2 Jahren

We are thrilled to announce a massive update to our Text-To-Speech (TTS) model for Twi! We are confident it is the best Twi TTS there now! Give it a listen and see if you agree! Sign up for our API and incorporate it into your products today! 🙏🏾 (link in bio)

We are thrilled to announce a massive update to our Text-To-Speech (TTS) model for Twi! We are confident it is the best Twi TTS there now! Give it a listen and see if you agree! Sign up for our API and incorporate it into your products today! 🙏🏾 (link in bio)

Ghana Natural Language Processing (NLP)

94,204 Aufrufe • vor 2 Jahren

.Joe Rogan: "Liberals and progressives want the War in Ukraine to be funded. They want to censor speech online. They want to give the World Health Organization, which is deeply influenced by Big Pharma, control over what we take and don't take. That's crazy! That's not what the liberals were when I was a kid. My parents were hippies. We lived in San Francisco during the Vietnam War. The liberals always wanted education and open-mindedness. The liberals at the ACLU let the Nazis talk and have a rally. They said you can't infringe on people's free speech because if you infringe on the free speech of people you disagree with, you're being a hypocrite. The only solution to bad speech is better speech. We've always known that. Everyone has to be able to talk, and we have to figure out who is right because you might be wrong, and you might be clinging to this idea that you are right, and you're going to do the whole thing a terrible disservice. When you have people who are supposedly progressive and liberal, and they are opposed to the idea that free speech is an absolute right as an American citizen. It's very, very important because too many people can decide what you can and can't say. Like when Tim Walz was saying, 'Free speech doesn't apply to hate speech and misinformation.' Of course, it does. But first of all, you said misinformation. If that is the case, where is all the punishment for people who spread misinformation during COVID? Where's the call for accountability? It doesn't exist. It's not real because they don't really care about misinformation. They care about controlling information."

.Joe Rogan: "Liberals and progressives want the War in Ukraine to be funded. They want to censor speech online. They want to give the World Health Organization, which is deeply influenced by Big Pharma, control over what we take and don't take. That's crazy! That's not what the liberals were when I was a kid. My parents were hippies. We lived in San Francisco during the Vietnam War. The liberals always wanted education and open-mindedness. The liberals at the ACLU let the Nazis talk and have a rally. They said you can't infringe on people's free speech because if you infringe on the free speech of people you disagree with, you're being a hypocrite. The only solution to bad speech is better speech. We've always known that. Everyone has to be able to talk, and we have to figure out who is right because you might be wrong, and you might be clinging to this idea that you are right, and you're going to do the whole thing a terrible disservice. When you have people who are supposedly progressive and liberal, and they are opposed to the idea that free speech is an absolute right as an American citizen. It's very, very important because too many people can decide what you can and can't say. Like when Tim Walz was saying, 'Free speech doesn't apply to hate speech and misinformation.' Of course, it does. But first of all, you said misinformation. If that is the case, where is all the punishment for people who spread misinformation during COVID? Where's the call for accountability? It doesn't exist. It's not real because they don't really care about misinformation. They care about controlling information."

KanekoaTheGreat

12,569,336 Aufrufe • vor 1 Jahr

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison Mati Staniszewski ElevenLabs

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison Mati Staniszewski ElevenLabs

Stripe

17,118 Aufrufe • vor 2 Monaten

RFK Jr. blasts Governor Walz for not understanding the first amendment: “We’re in a very frightening time now where we are seeing the normalization of censorship. I saw this quote Governor Walz, said last year where he said that the First Amendment is not absolute, that it does not protect misinformation or disinformation, and he is legally wrong there, it does protect that. The First Amendment protects speech, true speech, and it protects lies. It protects good speech, and it protects bad speech. It protects all speech.” They didn't pass the First Amendment to protect speech that everybody likes. They passed it to protect the speech that's inconvenient, that's abhorrent, that nobody wants to hear, that's dangerous.” “Louis Brandeis said that the remedy for bad speech, the remedy for lies is not censorship, it's more speech. If we don't understand that, we will lose democracy for sure.”

RFK Jr. blasts Governor Walz for not understanding the first amendment: “We’re in a very frightening time now where we are seeing the normalization of censorship. I saw this quote Governor Walz, said last year where he said that the First Amendment is not absolute, that it does not protect misinformation or disinformation, and he is legally wrong there, it does protect that. The First Amendment protects speech, true speech, and it protects lies. It protects good speech, and it protects bad speech. It protects all speech.” They didn't pass the First Amendment to protect speech that everybody likes. They passed it to protect the speech that's inconvenient, that's abhorrent, that nobody wants to hear, that's dangerous.” “Louis Brandeis said that the remedy for bad speech, the remedy for lies is not censorship, it's more speech. If we don't understand that, we will lose democracy for sure.”

End Tribalism in Politics

261,809 Aufrufe • vor 1 Jahr

Listen up 🔊 We’ve made some updates to our Gemini Audio models and capabilities: — Gemini’s live speech-to-speech translation capability is rolling out in a beta experience to the Google Translate app, bringing you real-time audio translation that captures the nuance of human speech — Gemini 2.5 Flash and 2.5 Pro Text-to-Speech preview models bring improved adherence to style prompts, precision pacing with context-aware speed adjustments, and character voice consistency for multi-speaker scenarios — Gemini 2.5 Flash Native Audio is now updated, with improvements to handle complex workflows, navigate user instructions, and hold natural conversations

Listen up 🔊 We’ve made some updates to our Gemini Audio models and capabilities: — Gemini’s live speech-to-speech translation capability is rolling out in a beta experience to the Google Translate app, bringing you real-time audio translation that captures the nuance of human speech — Gemini 2.5 Flash and 2.5 Pro Text-to-Speech preview models bring improved adherence to style prompts, precision pacing with context-aware speed adjustments, and character voice consistency for multi-speaker scenarios — Gemini 2.5 Flash Native Audio is now updated, with improvements to handle complex workflows, navigate user instructions, and hold natural conversations

Google AI

1,092,358 Aufrufe • vor 7 Monaten

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale blog: Large-scale generative models such as GPT and DALL-E have revolutionized natural language processing and computer vision research. These models not only generate high fidelity text or image outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are neither filtered nor enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale blog: Large-scale generative models such as GPT and DALL-E have revolutionized natural language processing and computer vision research. These models not only generate high fidelity text or image outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are neither filtered nor enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.

AK

429,307 Aufrufe • vor 3 Jahren

Glenn Beck: Real Strength of Free Nation Is Protecting Speech We Hate Not Just Speech We Love “If you outlaw the burning of a flag, you have placed the cloth above the constitution that it represents, you have made the flag an idol. We don't worship idols, if you can only praise the flag and never protest it, then it is stops being a symbol of freedom and starts being an idol of obedience. Now that's the argument for allowing it, at least to me, because the real strength of a free nation is how we protect not the speech we love, but how we endure the speech we hate…” – Glenn Beck

Glenn Beck: Real Strength of Free Nation Is Protecting Speech We Hate Not Just Speech We Love “If you outlaw the burning of a flag, you have placed the cloth above the constitution that it represents, you have made the flag an idol. We don't worship idols, if you can only praise the flag and never protest it, then it is stops being a symbol of freedom and starts being an idol of obedience. Now that's the argument for allowing it, at least to me, because the real strength of a free nation is how we protect not the speech we love, but how we endure the speech we hate…” – Glenn Beck

Vigilant Fox 🦊

47,801 Aufrufe • vor 10 Monaten

Trump: "We took the freedom of speech away because that's been through the courts and the courts said you have freedom of speech, but what has happened is when they burn a flag it agitates and irritates crowds."

Trump: "We took the freedom of speech away because that's been through the courts and the courts said you have freedom of speech, but what has happened is when they burn a flag it agitates and irritates crowds."

Aaron Rupar

955,693 Aufrufe • vor 9 Monaten

Milo Yiannopoulos “It doesn't matter if you agree with the literal truth of Christianity or not, the founders did and they made a country for people who did” “If you don't agree with that — you don't appreciate that we should not only restore Christianity in culture, but require it in public life, you should go to Canada.” This whole speech is 🔥

Milo Yiannopoulos “It doesn't matter if you agree with the literal truth of Christianity or not, the founders did and they made a country for people who did” “If you don't agree with that — you don't appreciate that we should not only restore Christianity in culture, but require it in public life, you should go to Canada.” This whole speech is 🔥

Wall Street Apes

1,786,922 Aufrufe • vor 9 Monaten

I created a channel point redeem that lets chat become the streamer and do live reacts. It pauses the stream and the chat's reaction is read out in text-to-speech.

I created a channel point redeem that lets chat become the streamer and do live reacts. It pauses the stream and the chat's reaction is read out in text-to-speech.

shindigs

463,210 Aufrufe • vor 2 Jahren