espnet
piper
espnet | piper | |
---|---|---|
15 | 39 | |
7,892 | 4,075 | |
1.3% | 14.0% | |
10.0 | 8.6 | |
1 day ago | 3 days ago | |
Python | C++ | |
Apache License 2.0 | 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.
espnet
-
WhisperSpeech – An Open Source text-to-speech system built by inverting Whisper
You might check out this list from espnet. They list the different corpuses they use to train their models sorted by language and task (ASR, TTS etc):
https://github.com/espnet/espnet/blob/master/egs2/README.md
-
[D] What's stopping you from working on speech and voice?
- https://github.com/espnet/espnet
- Íslensk talgervilsrödd sem hægt er að nota á Macca
-
High quality, fast performing, local text to speech generation
This link has instructions for doing this for a Japanese model. It would have to be altered to work with ljspeech and the fine tune dataset.
-
Text to speech generation
This work is made possible by the excellent advancements in text to speech modeling. ESPnet is a great project and should be checked out for more advanced and a wider range of use cases. This pipeline was also made possible by the great work from espnet_onnx in building a framework to export models to ONNX.
-
[P] TorToiSe - a true zero-shot multi-voice TTS engine
CMU WavLab has ESPNet https://espnet.github.io/espnet/ which includes a number of high quality TTS models including VITS (which in my subjective experience is just as good as what is demonstrated here). Also the inference on various ESPNet pretrained TTS models is reasonable and sentences take on average 5 seconds per word to generate the waveform on my totally mid PC setup.
-
How to get Job in NLP?
The reason I'm saying this is to point out that having and in-depth knowledge on speech processing/generation requires a lot of information about signal processing and human speech in general (eg. acoustics and phonetics). However, if you're not into learning everything there is to know about a subject, just take one state-of-the-art example and study that as best as you can. Pick one environment/toolkit, for example espnet and simply go with that.
-
Help picking a good speech recognition library
https://github.com/espnet/espnet (kind of like a newer Kaldi, but also not beginner friendly)
-
speechbrain VS espnet - a user suggested alternative
2 projects | 13 Oct 2021
both provide e2e ASR support but espnet does have more utilities where as speechbarain is clean
-
Need help with training ASR model from scratch.
This is relatively small amount of speech to train the model from scratch, but you can train using another pre-trained model for initialization. There are numbers of end-to-end ASR toolkits which can be used for this: https://github.com/NVIDIA/NeMo and https://github.com/espnet/espnet
piper
-
ESpeak-ng: speech synthesizer with more than one hundred languages and accents
Depending on your definition of "huge", you might find Piper TTS fits your requirements: https://github.com/rhasspy/piper
The size of the associated voice files varies but there are options that are under 100MB: https://huggingface.co/rhasspy/piper-voices/tree/main/en
-
WhisperSpeech – An Open Source text-to-speech system built by inverting Whisper
If you're not already aware, the primary developer of Mimic 3 (and its non-Mimic predecessor Larynx) continued TTS-related development with Larynx and the renamed project Piper: https://github.com/rhasspy/piper
Last year Piper development was supported by Nabu Casa for their "Year of Voice" project for Home Assistant and it sounds like Mike Hansen is going to continue on it with their support this year.
-
Coqui.ai Is Shutting Down
Coqui-ai was a commercial continuation of Mozilla TTS and STT (https://github.com/mozilla/TTS).
At the time (2018-ish), it was really impressive for on-device voice synthesis (with a quality approaching the Google and Azure cloud-based voice synthesis options) and open source, so a lot of people in the FOSS community were hoping it could be used for a privacy-respecting home assistant, Linux speech synthesis that doesn't suck, etc.
After Mozilla abandoned the project, Coqui continued development and had some really impressive one-shot voice cloning, but pivoted to marketing speech synthesis for game developers. They were probably having trouble monetizing it, and it doesn't surprise me that they shut down.
An equivalent project that's still in active development and doing really well is Piper TTS (https://github.com/rhasspy/piper).
-
OpenVoice: Versatile Instant Voice Cloning
There isn't an ElevenLabs app like that, but I think that's the most expedient method, by far.
(details and warning: in-depth, opinionated take, written almost for my own benefit, I've done a lot of work near here recently but haven't had to organize my thoughts until now)
Why? Local inference is hard. You need two things: the clips to voice model (which we have here, but bleeding edge), and text + voice -> speech model.
Text to voice to speech, locally, has excellent prior art for me, in the form of a Raspberry Pi-based ONNX inference library called [Piper](https://github.com/rhasspy/piper). I should just be able to copy that, about an afternoon of work!
Except...when these models are trained, they encode plaintext to model input using a library called eSpeak. eSpeak is basically f(plaintext) => ints representing phonemes. eSpeak is a C library and written in a style I haven't seen in a while and depends on other C libraries. So I end up needing to port like 20K lines of C to Dart...or I could use WASM, but over the last year, I lost the ability to be able to reason through how to get WASM running in Dart, both native and web.
It's a really annoying technical problem: the speech models all use this eSpeak C library to turn plaintext => model input (tokenized phonemes).
Re: ElevenLabs
I had looked into the API months ago and vaguely remembered it was _very_ complete.
I spent the last hour or two playing with it, and reconfirmed that. They have enough API surface that you could build an API that took voice recordings, created a voice, and then did POSTs / socket connection to get audio data from that voice at will.
Only issue is pricing IMHO, $0.18 for 1000 characters. :/ But this is something I feel very comfortable saying wouldn't be _that_ much work to build and open source with a "bring your own API key" type thing. I had forgotten about Eleven Labs till your post, which made me realize there was an actually meaningful and quite moving use case for it.
-
Hello guys, any selfhosted alternative to eleven labs?
piper (https://github.com/rhasspy/piper)
-
[D] What offline TTS Model is good enough for a realistic real-time task?
I have been using piper-tts and it is GREAT and super lightweight / easy to use. On a 2080 I'm sure you can use the HQ models no worries!
-
Easy implement TTS libary for cpp
So i found some library and one which is from github and have read.me or good documentation called piper (https://github.com/rhasspy/piper) so apparently this library is for rasbery pi and yes there is TXT function and i need to modify again to make it more simple but my simple project don't need this kind of big complex libary and all i need is what i said before just a function that can output sound from computer using c++ libary.
-
Piper-whistle – Tool for piper TTS voice model management
piper-whistle is a tool to manage voices used with the piper (https://github.com/rhasspy/piper) speech synthesizer. Main motivation was to download and reference models in a structured way. You may browse the docs online at https://think-biq.gitlab.io/piper-whistle/
-
StyleTTS2 – open-source Eleven Labs quality Text To Speech
You may want to try Piper for this case (RPi 4): https://github.com/rhasspy/piper
- Piper: A fast, local neural text to speech system
What are some alternatives?
speechbrain - A PyTorch-based Speech Toolkit
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
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)
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
k2 - FSA/FST algorithms, differentiable, with PyTorch compatibility.
espeak-ng - eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
silero-models - Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
kaldi-gstreamer-server - Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
mimic3 - A fast local neural text to speech engine for Mycroft
Kaldi Speech Recognition Toolkit - kaldi-asr/kaldi is the official location of the Kaldi project.
willow - Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative