marcus

stochastic/black-box optimization and super-resolution paper tweets

[Collabora @Collabora]

This #EarthDay we're taking a moment to highlight the incredible work that our environmental partners do daily. As @1PercentFTP members, we support them to secure a future for people and our planet.🌎➡️https://t.co/pClaQ5MgHT #onepercentfortheplanet

[Collabora @Collabora]

Open Source honored at Embedded World: Collabora's #WhisperFusion has been nominated for Embedded Award 2024! https://t.co/DXbrDiicn2

#OpenSource #AI #ML #TextToSpeech #AIChatbot

[Miguel Xochicale 🧑🏽‍🔬🤖〰️ @_mxochicale]

🔥 WhisperFusion: low latency conversations with an AI chatbot incorporating multiple optimization strategies such as torch.compile, TensorRT, Batching, Quantization, KV caching, Attention, Decoding, etc:
🐙 https://t.co/oKjzHRYPVv
📹 https://t.co/KyRyzVtyHB

@Collabora 🙏👇

[LAION @laion_ai]

BUD-E on Germany's biggest IT-Blog :) https://t.co/i0inNSFcZQ

[Collabora @Collabora]

While many companies have built their #machinelearning analysis framework around #GStreamer, no one had made the effort to contribute upstream, until now. Introducing the @GStreamer Analytics Metadata Framework: https://t.co/Du7JlFYag7

#OpenSource #DataAnalytics #ComputerVision

[Jakub Piotr Cłapa @jpclap]

I am on holiday while @Collabora’s Open Source WhisperSpeech TTS model landed on the top spot of Spaces this week on @huggingface ! Thanks a lot @_akhaliq for helping to spread the word 🚀

Meanwhile, v2 already started brewing… :)

[marcus @marcusedel]

@cocktailpeanut @josephpollack We are looking into supporting MPS, should be straightforward. You can track the progress here - https://t.co/7NtvpMhC1Y

[marcus @marcusedel]

@kolergy @_akhaliq We will release support for more languages soon, starting with French and German. @jpclap posted an example on the README already.

[marcus @marcusedel]

@realmrfakename @jpclap @_akhaliq Yes, that said, WhisperSpeech already supports voice cloning.

[AK @_akhaliq]

Collabora releases WhisperSpeech

demo: https://t.co/bLA17q4px5

Open Source text-to-speech system built by Collabora and LAION by inverting Whisper.

[Robert Scoble @Scobleizer]

A company working on the AI assistant latency problem.

Users will hate talking to AIs if they take 20 seconds to answer.

[Collabora @Collabora]

#AI news: By creating a real-time #AIChatbot communication system using fully #OpenSource tools, Collabora's engineers have addressed the unnatural delay in current bot interactions for seamless conversation! Meet #WhisperFusion: https://t.co/GGFLjg10Uw #ML #TextToSpeech

[Collabora @Collabora]

Coming up next week: the inaugural edition of #AIdotDev! Join us as Jakub Piotr Cłapa dives into findings from WhisperSpeech, a new #OpenSource text-to-speech model based entirely on properly licensed speech datasets & unrestricted code https://t.co/RP361aKLX9 #AI #ML @jpclap

[Vineet @imVsuryan]

Introducing MLBench, our versatile benchmarking system for machine learning frameworks. 🔄 Compare runtimes, track memory usage, and more effortlessly.
Explore MLBench in our latest blog: https://t.co/Rk8314dmcC
#MLBench #MachineLearning #CollaboraInnovation

[marcus @marcusedel]

@Collabora @jpclap @jpclap awesome ground work for a complete open source model

[Collabora @Collabora]

📢 New blog post! Meet the latest player in the text-to-speech field - WhisperSpeech, a proudly #opensource model: https://t.co/FnZ6FBlbAx #MachineLearning @jpclap

[Jakub Piotr Cłapa @jpclap]

Yesterday I had the pleasure to talk with Christoph Schuhmann from LAION about my https://t.co/9UUMmDCh90 model and the future of Open Source emotive text to speech. Big thanks to @Collabora for making this work possible.
https://t.co/IzfJg9SI7y

[marcus @marcusedel]

@Collabora @jpclap https://t.co/RDVy679dTr has all the details including a notebook to synthesis speech #TTS

[Collabora @Collabora]

Democratizing AI just dropped a new podcast episode: "Open Source Text-To-Speech Projects: WhisperSpeech - In Depth Discussion". Tune in to unpack the evolution of #WhisperSpeech in the #OpenSource world! ➡️https://t.co/Gq1OnF65gQ #machinelearning @jpclap

[marcus @marcusedel]

Unlock the Power of Words with https://t.co/WhqC7lpr3F Ever wished for a tool that turns hours of audio into concise summaries? At Collabora, we worked on a completely open source transcription, summarization, and translation pipeline. #machinelearning #transcription @imVsuryan