espnet
k2
Our great sponsors
espnet | k2 | |
---|---|---|
15 | 2 | |
7,852 | 1,035 | |
2.1% | 1.5% | |
10.0 | 7.2 | |
about 3 hours ago | 20 days ago | |
Python | Cuda | |
Apache License 2.0 | Apache License 2.0 |
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):
-
[D] What's stopping you from working on speech and voice?
- https://github.com/espnet/espnet
-
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.
-
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
You actually dont need to have phone level alignment for your data. Both hybrid and end-2-end approaches can work with utterance level alignment. For the hybrid approach, you would need a lexicon which maps each unique word in your training transcription to its phone sequence. You can obtain this with CMU's tool. For end-2-end approach you will need a byte pair encoder to tokenize the words in the transcriptions to its sub-words.
-
Is there a python based speaker diarization system you would recommend?
Have a look at this PR at ESPnet. It might be useful.
-
What are some good speech recognition papers I can implement?
espnet
k2
-
Differentiable Finite State Machines
This uses dense (soft/weighted) transitions from any state to any state, and then some regularization to guide it to more sparse solutions.
In practice, the number of states can be huge (thousands, maybe millions), so representing this as a dense matrix (a 1Mx1M matrix is way too big) is not going to work. It must be sparse, and in practice (all FST you usually deal with) it is. So it's very much a waste to represent it as a dense matrix.
That's why there are many specialized libraries to deal with FSTs. Also in combination with deep learning tools. See e.g. K2 (https://github.com/k2-fsa/k2).
-
What are some good speech recognition papers I can implement?
k2
What are some alternatives?
speechbrain - A PyTorch-based Speech Toolkit
NeMo - NeMo: a framework for generative AI
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
kaldi-gstreamer-server - Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
Kaldi Speech Recognition Toolkit - kaldi-asr/kaldi is the official location of the Kaldi project.
DeepSpeech - DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
flowtron - Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer
StarGANv2-VC - StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
Conv-TasNet - A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
Resemblyzer - A python package to analyze and compare voices with deep learning