正在加载视频...

视频加载失败

返回首页

IBM just released Granite 4.0 1B Speech, a compact and efficient speech-language model, designed for multilingual speech recognition and bidirectional speech translation. New #1 on the OpenASR leaderboard! It can even run in your browser on WebGPU, thanks to 🤗 Transformers.js

xenovacom's profile picture

Xenova

18,688 subscribers

21,506 次观看 • 3 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

We’re releasing access to Speech-1, our conversational speech model designed specifically for customer phone calls (8khz telephony) to reduce call drop rates.
0:18

We’re releasing access to Speech-1, our conversational speech model designed specifically for customer phone calls (8khz telephony) to reduce call drop rates.

MetaVoice

29,903 次观看 • 1 年前

Two free regenerations. You can now regenerate Text to Speech and Speech to Speech two more times for free on our site. If you're not happy with your first generation, adjust the style settings and regenerate at no additional cost. Read on for all the details:
0:18

Two free regenerations. You can now regenerate Text to Speech and Speech to Speech two more times for free on our site. If you're not happy with your first generation, adjust the style settings and regenerate at no additional cost. Read on for all the details:

ElevenLabs

67,089 次观看 • 1 年前

Meta's Segment Anything Model (SAM) can now run in your browser w/ WebGPU (+ fp16), meaning up to 8x faster image encoding (10s → 1.25s)! 🤯⚡️ Video is not sped up! Everything runs 100% locally thanks to 🤗 Transformers.js and onnxruntime-web! 🔗 Demo:
0:11

Meta's Segment Anything Model (SAM) can now run in your browser w/ WebGPU (+ fp16), meaning up to 8x faster image encoding (10s → 1.25s)! 🤯⚡️ Video is not sped up! Everything runs 100% locally thanks to 🤗 Transformers.js and onnxruntime-web! 🔗 Demo:

Xenova

120,352 次观看 • 2 年前

JUST IN: Meta AI introduces Voicebox, an all-in-one generative speech model. Voicebox is an impressive breakthrough! It could do for speech what other models like GPT-3 and Stable Diffusion have done for text and images. Some key details: - Voicebox can synthesize speech across 6 languages - It's a general-purpose model that can perform tasks it wasn't trained on. It can perform noise removal, content editing, style conversion, and more - Supports in-context text-to-speech synthesis and cross-lingual style transfer - It's 20x faster than current models and outperforms single-purpose models through in-context learning paper: blog:
0:13

JUST IN: Meta AI introduces Voicebox, an all-in-one generative speech model. Voicebox is an impressive breakthrough! It could do for speech what other models like GPT-3 and Stable Diffusion have done for text and images. Some key details: - Voicebox can synthesize speech across 6 languages - It's a general-purpose model that can perform tasks it wasn't trained on. It can perform noise removal, content editing, style conversion, and more - Supports in-context text-to-speech synthesis and cross-lingual style transfer - It's 20x faster than current models and outperforms single-purpose models through in-context learning paper: blog:

elvis

88,512 次观看 • 3 年前

The speech on the FREE open source Sesame text to speech is astonishing. It just killed Google’s voice project for podcasts and the monetization they hoped for. Here is a Hugging Face Gradio link to test: But download it and clone your voice!
0:17

The speech on the FREE open source Sesame text to speech is astonishing. It just killed Google’s voice project for podcasts and the monetization they hoped for. Here is a Hugging Face Gradio link to test: But download it and clone your voice!

Brian Roemmele

87,908 次观看 • 1 年前

France President Emmanuel Macron says “Free speech is bullsh*t” and slams tech companies for not letting them control the algorithms and not censoring what liberals consider “hate speech” “Some of them claim to be in favor of free speech — Free speech is pure bullsh*t — especially when it is guided from one hated speech to another hated speech” Liberals want to control the algorithms and censor anything they consider hate speech
0:18

France President Emmanuel Macron says “Free speech is bullsh*t” and slams tech companies for not letting them control the algorithms and not censoring what liberals consider “hate speech” “Some of them claim to be in favor of free speech — Free speech is pure bullsh*t — especially when it is guided from one hated speech to another hated speech” Liberals want to control the algorithms and censor anything they consider hate speech

Wall Street Apes

27,637 次观看 • 4 个月前

We’ve been working closely with OpenAI for the past few months to test the new Realtime API. I’m excited to share some thoughts on the best way to productize speech-to-speech for language learning, and announce the first thing we’ve built here, Live Roleplays. 🧵
0:15

We’ve been working closely with OpenAI for the past few months to test the new Realtime API. I’m excited to share some thoughts on the best way to productize speech-to-speech for language learning, and announce the first thing we’ve built here, Live Roleplays. 🧵

Andrew Hsu

390,004 次观看 • 1 年前

[to the tune of happy birthday] text turns into speech text turns into speech the model is launching text turns into speech
0:15

[to the tune of happy birthday] text turns into speech text turns into speech the model is launching text turns into speech

fofr

25,405 次观看 • 2 个月前

“Free Speech, free speech, free speech is a British Value & we have guarded it for Centuries” Yes Keir Starmer actually just said this.
0:11

“Free Speech, free speech, free speech is a British Value & we have guarded it for Centuries” Yes Keir Starmer actually just said this.

Concerned Citizen

11,040 次观看 • 8 个月前

Liberal Senator Anne Ruston says the hate speech bill has nothing to do with freedom of speech, arguing it was actually designed to target radical Islamic extremism and neo-Nazi groups.
0:16

Liberal Senator Anne Ruston says the hate speech bill has nothing to do with freedom of speech, arguing it was actually designed to target radical Islamic extremism and neo-Nazi groups.

Anthony Khallouf

48,161 次观看 • 5 个月前

Bytedance just dropped realtime voice translation 3x faster than before, with only a ~3s lag! Seed LiveInterp 2 is a full duplex speech-to-speech model with >70% correctness. When this makes it to video calls, it'll open up previously impossible connections.
0:11

Bytedance just dropped realtime voice translation 3x faster than before, with only a ~3s lag! Seed LiveInterp 2 is a full duplex speech-to-speech model with >70% correctness. When this makes it to video calls, it'll open up previously impossible connections.

Deedy

127,144 次观看 • 10 个月前

Just a reminder, Hitler rounded up the jews and put them in work camps. He didn’t debate them and let them run the media companies because of free speech. Concepts like free speech only work in homogeneous societies.
0:11

Just a reminder, Hitler rounded up the jews and put them in work camps. He didn’t debate them and let them run the media companies because of free speech. Concepts like free speech only work in homogeneous societies.

₱₳₮Ɽł₵₭ ₴ł₲ⱧØ₱

191,724 次观看 • 9 个月前

IT'S SPOOPY MONTH!👻 This new model is now available in my Ko-Fi c: All details in comments! Can be used as a model itself or as a pet for text-to-speech redeems Special thanks to @Kitty_Mama_TV and Eruben | Pinned new account for helping me test it! #ENVtuber #VTuberAssets #VTubeStudio
0:11

IT'S SPOOPY MONTH!👻 This new model is now available in my Ko-Fi c: All details in comments! Can be used as a model itself or as a pet for text-to-speech redeems Special thanks to @Kitty_Mama_TV and Eruben | Pinned new account for helping me test it! #ENVtuber #VTuberAssets #VTubeStudio

⛓️Hozshi V-Artist 🩵 COMMS CLOSED

46,381 次观看 • 1 年前

Also, you can now add the ability to talk to your agents. Cloudflare /voice adds real-time voice to the Agents SDK. ~30 lines of server code to get started, with built-in speech to text and text to speech on Workers AI.
0:10

Also, you can now add the ability to talk to your agents. Cloudflare /voice adds real-time voice to the Agents SDK. ~30 lines of server code to get started, with built-in speech to text and text to speech on Workers AI.

Anni Wang

10,932 次观看 • 2 个月前

🚨🇬🇧 WATCH: ENI ALUKO CLAIMS THE UK “HAS FREE SPEECH” Eni Aluko tried to explain Britain’s so-called speech laws on live TV - and it sounded like pure nonsense. 🔴 “Offensive” opinions are fine 🔴 But “grossly offensive” ones are criminal 🔴 Translation: It depends whether a judge likes you or not We don’t have free speech - we have conditional permission from the state.
0:15

🚨🇬🇧 WATCH: ENI ALUKO CLAIMS THE UK “HAS FREE SPEECH” Eni Aluko tried to explain Britain’s so-called speech laws on live TV - and it sounded like pure nonsense. 🔴 “Offensive” opinions are fine 🔴 But “grossly offensive” ones are criminal 🔴 Translation: It depends whether a judge likes you or not We don’t have free speech - we have conditional permission from the state.

British Intel

11,529 次观看 • 7 个月前

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.
0:17

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Akshay 🚀

31,216 次观看 • 5 个月前

🚨 NEW: Nigel Farage has used his maiden speech to call for a referendum on the ECHR
0:14

🚨 NEW: Nigel Farage has used his maiden speech to call for a referendum on the ECHR

Politics UK

1,064,480 次观看 • 1 年前

Today, President Trump traveled to Iowa to deliver a speech on the economy and energy. Nothing better than a speech about “energy” from a guy who sleeps all day 🙄 #FallonTonight
0:18

Today, President Trump traveled to Iowa to deliver a speech on the economy and energy. Nothing better than a speech about “energy” from a guy who sleeps all day 🙄 #FallonTonight

The Tonight Show

40,692 次观看 • 5 个月前