Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Xiaomi-CocktailASR-1 just landed on Hugging Face, many people yapping, one clean transcript 🍸 feed an audio with people speaking over each other, a clip of the voice to isolate, get the transcription from just that person ▶️ on Spaces

HuggingApps's profile picture

Hugging Apps

4,114 subscribers

11,126 Aufrufe • vor 9 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Xiaomi just dropped MiDashengLM-Gen on Hugging Face 🎬🔊 one prompt, six tagged views of a scene, caption, transcript, voice, music, sfx, room, and it renders the whole thing as a single 16kHz clip - the whole scene becomes allive, in audio ▶️ on Spaces
0:27

Xiaomi just dropped MiDashengLM-Gen on Hugging Face 🎬🔊 one prompt, six tagged views of a scene, caption, transcript, voice, music, sfx, room, and it renders the whole thing as a single 16kHz clip - the whole scene becomes allive, in audio ▶️ on Spaces

Hugging Apps

17,511 Aufrufe • vor 1 Monat

A startup with under 100 people just passed ElevenLabs, Gemini, and OpenAI on the voice leaderboards Cartesia took #1 on both speaking and listening in the same week. Sonic 3.5 for voice, Ink 2 for transcription👇
1:20

A startup with under 100 people just passed ElevenLabs, Gemini, and OpenAI on the voice leaderboards Cartesia took #1 on both speaking and listening in the same week. Sonic 3.5 for voice, Ink 2 for transcription👇

Nelly;

22,875 Aufrufe • vor 3 Monaten

Just got early access to Aleph, a new in-context video model from Runway. Here’s a snippet of my first experiment using a toy car. Audio added with the MMAudio Gradio demo on Hugging Face spaces
0:35

Just got early access to Aleph, a new in-context video model from Runway. Here’s a snippet of my first experiment using a toy car. Audio added with the MMAudio Gradio demo on Hugging Face spaces

William Lamkin

79,195 Aufrufe • vor 1 Jahr

Ctrl+F, but for sound 🔍🔊 SpotSound just landed on Hugging Face, give it a long recording and describe what you're looking for, and it will hand back the timestamps ▶️ on Spaces
0:23

Ctrl+F, but for sound 🔍🔊 SpotSound just landed on Hugging Face, give it a long recording and describe what you're looking for, and it will hand back the timestamps ▶️ on Spaces

Hugging Apps

30,028 Aufrufe • vor 1 Monat

Just another video of an Israeli Rabbi excitedly talking about starting a global war with the goal of having Christians & Muslims annihilate each other off the face of this earth. This is one of so many I’ve watched on this topic. But I am the one criticised for speaking about it. You show people factual historical evidence & you show them real footage of people saying these things themselves & still people deny it because they are brainwashed with propaganda.
1:47

Just another video of an Israeli Rabbi excitedly talking about starting a global war with the goal of having Christians & Muslims annihilate each other off the face of this earth. This is one of so many I’ve watched on this topic. But I am the one criticised for speaking about it. You show people factual historical evidence & you show them real footage of people saying these things themselves & still people deny it because they are brainwashed with propaganda.

Lozzy B 🇦🇺𝕏

53,659 Aufrufe • vor 6 Monaten

Free speech relies on knowing who’s actually speaking. Deepfakes break that. Give people copyright over their own face and voice. Clip from Sky News with Ridge & Frost 👇
0:41

Free speech relies on knowing who’s actually speaking. Deepfakes break that. Give people copyright over their own face and voice. Clip from Sky News with Ridge & Frost 👇

Jessaline 🇬🇧

24,763 Aufrufe • vor 8 Monaten

An open-weight alternative to ElevenLabs! Voxtral is a TTS model by Mistral with: - just 4B params - 70ms latency for voice agents - voice cloning from 3s of audio - 9 languages + cross-lingual transfer - 68.4% win rate over ElevenLabs Flash v2.5 Open weights on Hugging Face.
0:23

An open-weight alternative to ElevenLabs! Voxtral is a TTS model by Mistral with: - just 4B params - 70ms latency for voice agents - voice cloning from 3s of audio - 9 languages + cross-lingual transfer - 68.4% win rate over ElevenLabs Flash v2.5 Open weights on Hugging Face.

Avi Chawla

28,162 Aufrufe • vor 5 Monaten

Sky's Yousra Elbagir is on the border between South Africa and Zimbabwe speaking to people entering illegally, while just a few miles away, thousands of people from Malawi, Zimbabwe and other countries leave, some in fear of their lives. ▶️
2:36

Sky's Yousra Elbagir is on the border between South Africa and Zimbabwe speaking to people entering illegally, while just a few miles away, thousands of people from Malawi, Zimbabwe and other countries leave, some in fear of their lives. ▶️

Sky News

77,203 Aufrufe • vor 1 Monat

Mike Graham gets emotional speaking about the assassination of right-wing activist Charlie Kirk. "It's one of those days where you wake up and you just think: 'What is wrong with the world?'. Why can people not just get on without shooting each other?!" @iromg
1:46

Mike Graham gets emotional speaking about the assassination of right-wing activist Charlie Kirk. "It's one of those days where you wake up and you just think: 'What is wrong with the world?'. Why can people not just get on without shooting each other?!" @iromg

Talk

144,049 Aufrufe • vor 1 Jahr

This clip is one tight slap on the face every honest citizen of India courtesy the judiciary The person sitting like an emperor with feet on the stool with people bowing to him is a convicted criminal ostensibly out on parole citing ill health 🤬
0:57

This clip is one tight slap on the face every honest citizen of India courtesy the judiciary The person sitting like an emperor with feet on the stool with people bowing to him is a convicted criminal ostensibly out on parole citing ill health 🤬

Sameer

53,220 Aufrufe • vor 1 Jahr

Jillian Michaels just told an entire room of conservatives that they need to get out of their echo chamber and talk to people on the other side.
1:25

Jillian Michaels just told an entire room of conservatives that they need to get out of their echo chamber and talk to people on the other side.

Anna Matson

65,263 Aufrufe • vor 1 Jahr

"It's just been cool to be around a person like that because there's not really too many people out in the world like him. He's really one of one." Breece Hall on his relationship with Aaron Rodgers:
0:46

"It's just been cool to be around a person like that because there's not really too many people out in the world like him. He's really one of one." Breece Hall on his relationship with Aaron Rodgers:

SNY Jets

49,729 Aufrufe • vor 1 Jahr

.Truffle Security co-founder and CEO Dylan Ayrey on the danger of exposed credentials and the Hugging Face incident: "We partnered with Hugging Face to clean up credentials that had been exposed in training sets people hosted on their platform." "There were about a quarter million live keys, many of which had direct supply chain implications." "There was a foundational Linux library that one of the keys had direct push access to. It could have pushed malware to most machines on the planet." "While in the middle of doing that, the CTO of Hugging Face shoots me a note, 'There's this OpenAI thing that just happened, take a look.'" "And sure enough, the first thing listed in the incident response was stolen credentials. The path of least resistance is always the first step." Dylan
1:01

.Truffle Security co-founder and CEO Dylan Ayrey on the danger of exposed credentials and the Hugging Face incident: "We partnered with Hugging Face to clean up credentials that had been exposed in training sets people hosted on their platform." "There were about a quarter million live keys, many of which had direct supply chain implications." "There was a foundational Linux library that one of the keys had direct push access to. It could have pushed malware to most machines on the planet." "While in the middle of doing that, the CTO of Hugging Face shoots me a note, 'There's this OpenAI thing that just happened, take a look.'" "And sure enough, the first thing listed in the incident response was stolen credentials. The path of least resistance is always the first step." Dylan

a16z

35,221 Aufrufe • vor 1 Monat

Audio of Trump on Gaza: I’d like Egypt to take people and I’d like Jordan to take people. You're talking about a million and half people, and we just clean out that whole thing…
0:49

Audio of Trump on Gaza: I’d like Egypt to take people and I’d like Jordan to take people. You're talking about a million and half people, and we just clean out that whole thing…

Acyn

2,969,087 Aufrufe • vor 1 Jahr

“It was just an absolutely gut-wrenching, heart-wrenching experience, one that has actually been difficult for me to tell other people about... It was one of the most remarkable displays I've seen of his leadership." Jake Sullivan Archived on Biden speaking to the families of hostages
1:38

“It was just an absolutely gut-wrenching, heart-wrenching experience, one that has actually been difficult for me to tell other people about... It was one of the most remarkable displays I've seen of his leadership." Jake Sullivan Archived on Biden speaking to the families of hostages

The Briefing with Jen Psaki

132,357 Aufrufe • vor 2 Jahren

Payton Tolle on supporting The Jimmy Fund ❤️ "It means a lot to me because I think about all the people that have helped out my family through my mom's battle with cancer... it affects so many more people than just that one person." Donate:
1:05

Payton Tolle on supporting The Jimmy Fund ❤️ "It means a lot to me because I think about all the people that have helped out my family through my mom's battle with cancer... it affects so many more people than just that one person." Donate:

NESN

76,933 Aufrufe • vor 1 Monat