TestDanRun @testdanrun
Coding all day long Joined October 2019-
Tweets43
-
Followers6
-
Following97
-
Likes485
@shinjiw_at_cmu Exciting! What will the next bound of OWSM be?
Transcribes and summarizes meetings locally github.com/Zackriya-Solut…
Transcribes audio into notes on your infrastructure github.com/murtaza-nasir/…
@alphacep I had pretty much the same intuition as well. I think FAIR's approach with the Omnilingual models lead to great performance for REALLY low-resource languages, but not so much for pushing performance for high-resource and even mid-resource languages.
@unilightwf What does this mean? So they tested to see if evaluators would mistake the human voice as synthetically generated? And out of all the tests, only 78.33% of the human voices in LJSpeech were identified as real voices?
@huckiyang @icmlconf @chenwanch1 @MXzBFhjFpS1jyMI @shinjiw_at_cmu @WavLab @NVIDIAAI That sounds interesting! I'm also interested in finding out what's a good distribution of data across languages to train a good multilingual ASR/AST model!
@chenwanch1 @LTIatCMU @nvidia Congratulations!! Can't wait to try the models out as a fellow ASR and Rowlet enthusiast!!
🎵 Introducing InspireMusic – an open-source music generation toolkit from Tongyi Lab, designed as an all-in-one AIGC toolkit for music, song, and audio creation. Whether you're a researcher, developer, or music enthusiast, InspireMusic has something for you: For researchers and developers: Train and fine-tune music/song/audio generation models with ease, optimizing the creative output. For music lovers: An intuitive tool to create music, songs, or audio content using text descriptions or audio prompts. 🚀 What's special about InspireMusic? ·Unified Audio Generation Framework: Powered by advanced generative model technology, InspireMusic supports music, song, and audio generation, offering diverse possibilities. ·Flexible and Controllable Output: Generate music with precise style and structure by using text prompts and musical feature descriptions. ·Simple and User-Friendly: Streamlined tools for model fine-tuning and inference, ensuring efficient training and improvements. ✨ Try it out now! 🎵 GitHub Repository: github.com/FunAudioLLM/In…🎶 Online Experience: 🤗HuggingFace Spaces: huggingface.co/spaces/FunAudi… ♪ Demo Page: iris2c.github.io/InspireMusic Start creating your own musical masterpiece today! 🎶
@mhnt1580 Awesome! I am still wrapping my head around the "content usefulness" axis though. For sound especially, would it be right to say if there are enough to sounds to form a scene, it would be a useful content?
@alphacep I'm wondering, given how performant Whisper is, are there still substantial benefits to pre-train and finetune your own self-supervised model, or would we get better results just from finetuning Whisper?
@unilightwf Hello! I'm interested in building speech evaluation frameworks! Could you provide some details? :)
Introducing Eagle-7B Based on the RWKV-v5 architecture, bringing into opensource space, the strongest - multi-lingual model (beating even mistral) - attention-free transformer today (10-100x+ lower inference) With comparable English performance with the best 1T 7B models
We are organizing The Speaker and Language Recognition Workshop (Odyssey) 2024, which will be held in Canada. The theme, "No Speaker Left Behind", underscores our commitment to overcoming disparities that affect individuals with diverse accents, backgrounds, or speech variations.
Excited to share you can now finetune over 1100+ TTS models thanks to @AIatMeta's MMS and the library shared below! In my experiments, you can get an excellent finetuned version of every MMS checkpoint takes just 20 minutes, with as few as 80 to 150 samples, across all models.
A week ago one of our customers handed us 1000 pages of this (10,000 more to come), and asked us for RAG solution. We said yes - because we said yes before we saw the document. But we've solved it - and there's a chance it's a strong improvement on all RAG SoTA.
@lileics Ahh, I wasn't able to make it. Would you be sharing the slides?
Happy to share our paper "Speaking Style Conversion with Discrete Self-Supervised Units" got accepted to #EMNLP2023 🌟 Project page - pages.cs.huji.ac.il/adiyoss-lab/di… W/ @adiyossLC (1/n) 🧵👇
Huck Yang @huckiyang
906 Followers 806 Following Sr. Staff Research Scientist | @GeorgiaTech | Past: @NvidiaAI @GoogleAI @Amazon @Hitachi TSMC | 🗣️ omni
Nicholas Neo @thatnicneo
2 Followers 62 Following
kyutai @kyutai_labs
26K Followers 14 Following
Kimi.ai @Kimi_Moonshot
181K Followers 136 Following Built by Moonshot AI to empower everyone to be superhuman. ⚡️API: https://t.co/XCrgjXAqMw @KimiProduct where we share cool use cases. @Kimidevs built for developers
Richard Palethorpe @jichiep
565 Followers 224 Following Working on LocalAI and LocalVQE. I wrote a Linux kernel exploit for an n-day once.
TensorTonic @TensorTonic
8K Followers 1 Following Infrastructure to run ML & GPU algorithms in cloud-native sandboxes
Puyuan Peng @PuyuanPeng
2K Followers 522 Following Research Scientist @Meta Superintelligence Lab. Speech & Audio. Previously @utaustin @uchicago @bnu_1902
BUT Speech @ButSpeech
716 Followers 294 Following We do impactful research and raise new leading scientific personalities in the field of speech processing.
Gary Wang @garygarywang
330 Followers 363 Following Speech, TTS & Gemini @google. Ex chemical Engineer (fuel cells, batteries, oil & gas). Now speech Synthesis, ASR, RL, NLP.
Samuele Cornell @SamueleCornell
980 Followers 524 Following Post-doc @ CMU LTI. Audio and speech researcher.
Rohan Paul @rohanpaul_ai
151K Followers 7K Following Compiling in real-time, the race towards AGI. The Largest Show on X for AI. 🗞️ Get my daily AI analysis newsletter to your email 👉 https://t.co/6LBxO8215l
Chubby♨️ @kimmonismus
122K Followers 3K Following Dream realized! Turned my love for AI into a career - sharing daily. Get my newsletter (225k+ subs): 🔗 https://t.co/jHMmImnfVg //📧 [email protected]
Yann LeCun @ylecun
1.2M Followers 787 Following Professor at NYU & Executive Chairman at AMI Labs. Ex-Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
Anurag Kumar @AcouIntel
2K Followers 292 Following Research Scientist, @GoogleDeepMind | Prev: @AIatMeta | CMU @SCSatCMU | @IITKanpur | Audio/Speech, Multimodal AI
Wen-Chin Huang @unilightwf
1K Followers 659 Following 名古屋大学情報学研究科助教. Assistant professor, Nagoya University. Speech synthesis & evaluation. Trilingual, street dancer, golfer. Tweets are my own opinions.
Piotr Żelasko @PiotrZelasko
2K Followers 735 Following AI + Speech @ Nvidia. PhD @ AGH-UST, ex-JHU. My interests: speech processing technology; ML/AI software engineering. Building OSS for Speech AI.
Desh Raj @rdesh26
4K Followers 2K Following Speech + LLMs @nvidia | Previously: @Meta MSL, @jhuclsp, @IITGuwahati
Sakana AI @SakanaAILabs
135K Followers 0 Following Building Frontier AI in Japan Try Sakana Chat, Marlin, Fugu 🐡 → https://t.co/1m2lSgnfB2
Audio and Speech Proc... @AudioAndSpeech
742 Followers 2 Following New Audio and Speech Processing papers from https://t.co/mvy2Lc7qxl: processing signals representing audio. Thank you to arXiv for use of its open access interoperability.
William Chen @chenwanch1
869 Followers 439 Following PhD Student @LTIatCMU @SCSatCMU | Masters @LTIatCMU | Formerly @TXInstruments | @UCF ‘21
Language Technologies... @LTIatCMU
12K Followers 237 Following The Language Technologies Institute in Carnegie Mellon University's @SCSatCMU
Alibaba_SpeechAI @TONGYI_SpeechAI
2K Followers 88 Following As part of Alibaba's Tongyi Lab, we focus on multimodal speech and language models like FunAudioLLM, FunASR, and CosyVoice. Explore our 200+ open-source models!
merve @mervenoyann
88K Followers 5K Following (mer-veh) open-sourceress at @huggingface 🧙🏻♀️ DM me for any feedback about HF 🤗 https://t.co/MhrMkGTm7p
bteo @bteo98
1 Followers 38 Following
Huck Yang @huckiyang
906 Followers 806 Following Sr. Staff Research Scientist | @GeorgiaTech | Past: @NvidiaAI @GoogleAI @Amazon @Hitachi TSMC | 🗣️ omni
Roshan Sharma @RoshanSSharma2
414 Followers 372 Following Research Scientist @GoogleDeepMind | PhD @CMU_ECE | #SpeechProc #NLProc | Previously @AIatMeta @Qualcomm
Alex Xu @alexxubyte
291K Followers 569 Following Co-Founder of ByteByteGo | Author of the bestselling book series: ‘System Design Interview’ | YouTube: https://t.co/9gPSJSrtPU
Alexander H. Liu @alex_h_liu
712 Followers 183 Following building talking machines @thinkymachines prev: @MistralAI @MITEECS
DCASE Challenge @DCASE_Challenge
717 Followers 29 Following Challenge on Detection and Classification of Acoustic Scenes and Events https://t.co/j9544Zu0yJ https://t.co/cQqlshpkU7…
Lilian Weng @lilianweng
263K Followers 182 Following Co-founder of Thinking Machines Lab @thinkymachines; Ex-VP, AI Safety & robotics, applied research @OpenAI; Author of Lil'Log
Lei Li @lileics
7K Followers 450 Following Generative AI for language and science. MT, LLM, GenAI Safety, Drug Discovery
🎙Jean-Louis Quegui... @JiliJeanlouis
6K Followers 5K Following Founder & CEO @gladia_io building audio AI infra I 🇫🇷 🇺🇸
Graham Neubig @gneubig
44K Followers 779 Following Associate professor @LTIatCMU. Co-founder/chief scientist @OpenHandsDev. I mostly work on modeling language.
Berkeley Biological &... @BerkeleySCLab
1K Followers 506 Following Lab @UCBerkeley for biological and artificial language. PI @begusgasper
Wei-Ning Hsu @mhnt1580
2K Followers 145 Following Research Scientist @ Meta FAIR / audio generation, self-supervised learning, speech processing
Hung-yi Lee (李宏�... @HungyiLee2
5K Followers 21 Following Hung-yi Lee is currently a professor at National Taiwan University. He owns a YouTube channel teaching deep learning in Mandarin.
Shammur Absar @shammur_absar
245 Followers 389 Following Research Scientist - QCRI. Interested in Conversational AI, Speech Processing, and NLP
IEEE ICASSP @ieeeICASSP
5K Followers 1 Following IEEE International Conference on Acoustics, Speech, and Signal Processing. #ICASSP2026 will be held 4-8 May 2026 in Barcelona, Spain.
Martin Andrews @_mdda_
991 Followers 2K Following AI Research / Founder @ Red Dragon AI. Co-organiser of Machine Learning Singapore MeetUp. @GoogleDevExpert (ML). Fixed Income quant in NYC during AI winter
Sam Witteveen @Sam_Witteveen
23K Followers 2K Following Co-founder @ Red Dragon AI, Google Developer Expert for Machine Learning/ Deep Learning,
Gašper Beguš @begusgasper
9K Followers 2K Following Assoc. Professor @UCBerkeley Interpretable AI and language @Interpret_AI PI @BerkeleySCLab Linguistics Lead @ProjectCETI🐳 College Principal of Bowles🏰
VoiceConversionLab @VoiceConversion
636 Followers 0 Following Introduce state of the art Voice Conversion researches 🧐
Jonathan Ho @hojonathanho
5K Followers 236 FollowingTrends for United States
You might like
