Vineel Pratap (@vineelk) header
Vineel Pratap (@vineelk) profile picture
Mountain View, CA
Joined June 2010
Photo by Vineel Pratap (@vineelk)Photo by Vineel Pratap (@vineelk)Photo by Vineel Pratap (@vineelk)Photo by Vineel Pratap (@vineelk)
🚀🚀🚀
Big update: @WaveFormsAI was acquired by @Meta. Today at #MetaConnect, you’ll see a little of what we’ve all been building. ✨🤖
1
4
478
Vineel Pratap retweeted
MLX got an official website!
25
73
15
901
92,006
At @WaveFormsAI we are #hiring in SF for: 1) Software Engineer, LiveKit/FastAPI Engine 2) Software Engineer, Full-Stack (React/FastAPI) 3) Research Engineer, Multimodal LLMs Join us to hear the AGI ! 🤖🎙️🪄 linkedin.com/company/wavefor…
8
2
3
60
20,479
Thrilled to be part of the @WaveFormsAI team, crafting magic with Audio LLMs !
Excited to announce the creation of WaveForms AI (waveforms.ai) – an Audio LLM company aiming to solve the Speech Turing Test and bring Emotional Intelligence to AI @WaveFormsAI
1
11
3,732
Vineel Pratap retweeted
We are releasing MMS Zero-shot: a model to transcribe the speech of almost any language using only a small amount of unlabeled text in the new language. Paper: arxiv.org/abs/2407.17852 Demo: huggingface.co/spaces/mms-me… Code/model: github.com/facebookresearch/…
6
32
6
197
95,614
Vineel Pratap retweeted
Just in time for the holidays, we are releasing some new software today from Apple machine learning research. MLX is an efficient machine learning framework specifically designed for Apple silicon (i.e. your laptop!) Code: github.com/ml-explore/mlx Docs: ml-explore.github.io/mlx/bui…
95
671
135
4,375
962,041
MMS TTS models have just been released through the Transformers library 🤗. Stay tuned for our upcoming finetuning recipe! Huge thanks to @sanchitgandhi99 and the amazing HuggingFace team for making MMS models accessible and user-friendly. 🌐
🤗 Transformers just got 1100+ new TTS checkpoints 🚀 You can now run any of @MetaAI's MMS TTS checkpoints using the Transformers library in 3 lines of code⚡️ MMS is a the largest democratizer of TTS globally to date 🌎 Try it in your language now: colab.research.google.com/gi…
1
4
7
2,122
Vineel Pratap retweeted
Happy to be releasing Code Llama! We've built it on Llama 2 and improved it for code use cases. In particular it supports infilling out of the box, and was trained with sequences up to 16k tokens. Looking forward to what the community will build with it! 1/7
9
40
2
244
33,525
Vineel Pratap retweeted
PaLM + AudioLM = AudioPaLM ! We start from PaLM pretrained on text and extend its vocab w/ audio tokens. This model can then be finetuned on a mix of any (speech, text) task e.g. ASR, TTS, MT and speech2speech translation in one's voice! 🧵1/4 google-research.github.io/se…
2
34
8
143
41,275
Vineel Pratap retweeted
The MMS models are now available on HuggingFace!
Meta AI's recently released "Massively Multilingual Speech" (MMS) model is a huge step forward towards democratizing Speech to every corner of the globe. In addition, it might also play a significant role in preserving global linguistic diversity. huggingface.co/papers/2305.1… 👇
1
13
1,235
Massively Multilingual Speech (MMS) demo is now on @huggingface Spaces! Try out speech-to-text and text-to-speech in over 1,100 languages! Demo 🤗 huggingface.co/spaces/mms-me… Docs 📝 huggingface.co/docs/transfor…
3
26
1
98
14,284
5 / 5 We've integrated MMS into 🤗Transformers making the models very easy to use for both inference and fine-tuning. Demo 👉 huggingface.co/spaces/facebo… Docs 👉 huggingface.co/docs/transfor… Fine-Tuning 👉 huggingface.co/blog/mms_adap…
5
12
680
Vineel Pratap retweeted
Introducing Voicebox, a new breakthrough generative speech system based on Flow Matching, a new method proposed by Meta AI. It can synthesize speech across six languages, perform noise removal, edit content, transfer audio style & more. More details on this work & examples ⬇️

46
414
116
1,722
445,400
Vineel Pratap retweeted
Excited to share the ToolBench, an evaluation suite for LLM tool manipulation capabilities. - Paper: arxiv.org/abs/2305.16504 - Code: github.com/sambanova/toolben… - Hugging Face leaderboard: huggingface.co/spaces/qianto…
17
1
68
25,824
We do open source many tools for CTC forced alignment as part of the MMS project. API: pytorch.org/audio/main/gener… (implemented for both CPU & GPU) Tutorial: pytorch.org/audio/main/tutor… Working with long audio files: github.com/facebookresearch/… (Compatible with any input language)
This Post is from an account that no longer exists. Learn more
1
3
12
1,225
😭 This is beautiful, it even supports text-to-speech and asr in tarifit, in both arabic and latin scripts... Clearly this was built with love 😭
MMS: Massively Multilingual Speech. - Can do speech2text and text speech in 1100 languages. - Can recognize 4000 spoken languages. - Code and models available under the CC-BY-NC 4.0 license. - half the word error rate of Whisper. Code+Models: github.com/facebookresearch/… Paper: scontent-lga3-2.xx.fbcdn.net… Blog: ai.facebook.com/blog/multili…
2
2
7
1,620
Vineel Pratap retweeted
MMS: Massively Multilingual Speech. - Can do speech2text and text speech in 1100 languages. - Can recognize 4000 spoken languages. - Code and models available under the CC-BY-NC 4.0 license. - half the word error rate of Whisper. Code+Models: github.com/facebookresearch/… Paper: scontent-lga3-2.xx.fbcdn.net… Blog: ai.facebook.com/blog/multili…
160
1,075
217
5,169
1,568,430
10x everything !
New work! The Massively Multilingual Speech (MMS) project scales speech technology to 1,100-4,000 languages using self-supervised learning with wav2vec 2.0. Paper: research.facebook.com/public… Blog: ai.facebook.com/blog/multili… Code/models: github.com/facebookresearch/…
2
3
6
1,126