seamless_communication
pyannote-audio
seamless_communication | pyannote-audio | |
---|---|---|
11 | 15 | |
10,393 | 5,315 | |
1.7% | 4.5% | |
8.6 | 8.7 | |
3 days ago | 2 days ago | |
Jupyter Notebook | Jupyter Notebook | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
seamless_communication
- FLaNK Stack for 04 December 2023
-
This week in AI - all the Major AI developments in a nutshell
Meta AI introduced a suite of AI language translation models that preserve expression and improve streaming [Details | GitHub]: SeamlessExpressive enables the transfer of tones, emotional expression and vocal styles in speech translation. You can try a demo of SeamlessExpressive using your own voice as an input here. SeamlessStreaming, a new model that enables streaming speech-to-speech and speech-to-text translations with <2 seconds of latency and nearly the same accuracy as an offline model. In contrast to conventional systems which translate when the speaker has finished their sentence, SeamlessStreaming translates while the speaker is still talking. t intelligently decides when it has enough context to output the next translated segment. SeamlessM4T v2, a foundational multilingual & multitask model for both speech & text. It's the successor to SeamlessM4T, demonstrating performance improvements across ASR, speech-to-speech, speech-to-text & text-to-speech tasks. Seamless, a model that merges capabilities from SeamlessExpressive, SeamlessStreaming and SeamlessM4T v2 into one.
-
Seamless: Meta's New Speech Models
The license details are listed on the project GitHub
https://github.com/facebookresearch/seamless_communication#l...
-
Open Source Libraries
facebookresearch/seamless_communication: Speech translation
- FLaNK Stack Weekly 28 August 2023
-
Meta: Code Llama, an AI Tool for Coding
I wish that Meta would release models like SeamlessM4T[0] under the same license as llama, or an even better one.
There seem to be opportunities for people to use technology like this to improve lives, if it were licensed correctly, but I don't see how any commercial offering would compete with anything that Meta does.
Whisper is licensed more permissively and does a great job with speech to text in some languages, and it can translate to English only, but it can't translate between a large number of languages, and it doesn't have any kind of text to speech or speech to speech capabilities.
[0]: https://github.com/facebookresearch/seamless_communication
-
Meta introduces SeamlessM4T, a foundational multimodal model that seamlessly translates and transcribes across speech and text for up to 100 languages
What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200 languages, unified speech-to-speech translation models have yet to achieve similar strides. More specifically, conventional speech-to-speech translation systems rely on cascaded systems composed of multiple subsystems performing translation progressively, putting scalable and high-performing unified speech translation systems out of reach. To address these gaps, we introduce SeamlessM4T—Massively Multilingual & Multimodal Machine Translation—a single model that supports speech- to-speech translation, speech-to-text translation, text-to-speech translation, text-to-text translation, and automatic speech recognition for up to 100 languages. To build this, we used 1 million hours of open speech audio data to learn self-supervised speech representations with w2v-BERT 2.0. Subsequently, we created a multimodal corpus of automatically aligned speech translations, dubbed SeamlessAlign. Filtered and combined with human- labeled and pseudo-labeled data (totaling 406,000 hours), we developed the first multilingual system capable of translating from and into English for both speech and text. On Fleurs, SeamlessM4T sets a new standard for translations into multiple target languages, achieving an improvement of 20% BLEU over the previous state-of-the-art in direct speech-to-text translation. Compared to strong cascaded models, SeamlessM4T improves the quality of into-English translation by 1.3 BLEU points in speech-to-text and by 2.6 ASR-BLEU points in speech-to-speech. On CVSS and compared to a 2-stage cascaded model for speech- to-speech translation, SeamlessM4T-Large’s performance is stronger by 58%. Preliminary human evaluations of speech-to-text translation outputs evinced similarly impressive results; for translations from English, XSTS scores for 24 evaluated languages are consistently above 4 (out of 5). For into English directions, we see significant improvement over Whisper- Large-v2’s baseline for 7 out of 24 languages. To further evaluate our system, we developed Blaser 2.0, which enables evaluation across speech and text with similar accuracy compared to its predecessor when it comes to quality estimation. Tested for robustness, our system performs better against background noises and speaker variations in speech-to-text tasks (average improvements of 38% and 49%, respectively) compared to the current state-of-the-art model. Critically, we evaluated SeamlessM4T on gender bias and added toxicity to assess translation safety. Compared to the state-of-the-art, we report up to 63% of reduction in added toxicity in our translation outputs. Finally, all contributions in this work—including models, inference code, finetuning recipes backed by our improved modeling toolkit Fairseq2, and metadata to recreate the unfiltered 470,000 hours of SeamlessAlign —are open-sourced and accessible at https://github.com/facebookresearch/seamless_communication
- Seamless Communication – new translation (text, speech) model from Facebook
-
Meta Releases SeamlessM4T, a Multimodal AI Model for Speech and Text Translation
281M and 235M param models too.
https://github.com/facebookresearch/seamless_communication/b...
I don't really know how the metrics they list compare to whisper, I'm very curious if these are fast enough for realtime speech2text? I think whisper technically could but it was difficult to do or something like that?
-
SeamlessM4T: All-in-one multimodal translation model
code: https://github.com/facebookresearch/seamless_communication
paper: https://ai.meta.com/research/publications/seamless-m4t/
demo: https://seamless.metademolab.com/
pyannote-audio
-
Open Source Libraries
pyannote/pyannote-audio
-
AI Transcribing tool for video with two voices?
Open Source. I've found this to be pretty nice, which is just a wrapper on some hugging face models https://github.com/pyannote/pyannote-audio
-
Show HN: PodText.ai – Search anything said on a podcast, Highlight text to play
(not the creator, but I've built something similar for personal use)
This is a great library for determining which speaker is speaking during each time in an audio file (this is called speaker diarization); I imagine they used it or something like it. Works really well out of the box!
https://github.com/pyannote/pyannote-audio
-
I wanted to use OpenAI's Whisper speech-to-text on my Mac without installing stuff in the Terminal so I made MacWhisper, a free Mac app to transcribe audio and video files for easy transcription and subtitle generation. Would love to hear some feedback on it!
Do you think pyannote could be implemented in the Pro version of the app to support diarization?
- I won several speaker diarization challenges with pyannote.audio
-
I made a free transcription service powered by Whisper AI
Free startup idea: Use Whisper with pyannote-audio[0]’s speaker diarization. Upload a recording, get back a multi-speaker annotated transcription.
Make a JSON API and I’ll be your first customer.
[0] https://github.com/pyannote/pyannote-audio
-
Can Whisper differentiate between different voices?
Whisper can’t, but pyannote-audio can. I’ve seen a couple of prototypes out there which link the two together.
-
[D] Is there a way to distinguish different human voices from 1 audio file ?
You can use pyannote python library. It will identify different speakers from audio and will create small audio files with those speakers.
- Post-Game Analysis: Destiny & Alex VS Andrew & Zen Shapiro
-
A quick and dirty tool for automatically analyzing speaking time in online debates (Effortpost)
This Colab notebook is basically a standard template (with small changes) provided by pyannote-audio, the library implementing the speaker diarization functionality we need. (template)
What are some alternatives?
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
supervision - We write your reusable computer vision tools. 💜
speechbrain - A PyTorch-based Speech Toolkit
ai-town - A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.
Resemblyzer - A python package to analyze and compare voices with deep learning
aider - aider is AI pair programming in your terminal
Kaldi Speech Recognition Toolkit - kaldi-asr/kaldi is the official location of the Kaldi project.
llama-gpt - A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
inaSpeechSegmenter - CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.
lmdeploy - LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
uis-rnn - This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.