wenet
functorch
wenet | functorch | |
---|---|---|
5 | 3 | |
3,691 | 397 | |
1.4% | - | |
9.6 | 9.7 | |
7 days ago | over 2 years ago | |
Python | C++ | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" 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.
wenet
-
Open Source Libraries
wenet-e2e/wenet
-
Deploying speech recognition models at scale
Try wenet wenet
-
Ask HN: Are there any good open source Text-to-Speech tools?
For STT, take a look at Wenet: https://github.com/wenet-e2e/wenet
They provide support for running in a Raspberry Pi and it runs in real-time. I have tried the desktop version and the quality is good enough when the audio is clean.
- Project Alice – an open source virtual assistant that can run offline
- Wenet results on Gigaspeech - on par with best results (Espnet). Pretrained model is available .
functorch
- Functorch: Jax-like composable function transforms for PyTorch
-
[P] Announcing Equinox! Filtered transformations + callable PyTrees = elegant neural networks in JAX
By the way, those aren't really inherent to functional programming/Jax - this is an implementation of those (at least grad/vmap/jvp/etc.) in PyTorch: https://github.com/facebookresearch/functorch
-
[Discussion] What do you like or dislike about RL Systems/Frameworks? TF, PyTorch, JAX, RLLib, Acme, SEED
If you want vmap in PyTorch, you can check out https://github.com/facebookresearch/functorch. It’s largely an imitation of Jax’s API, but in PyTorch.
What are some alternatives?
vosk-api - Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
equinox - Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
silero-models - Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
FasterTransformer - Transformer related optimization, including BERT, GPT
ncnn - ncnn is a high-performance neural network inference framework optimized for the mobile platform
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
Open3D - Open3D: A Modern Library for 3D Data Processing
fstalign - An efficient OpenFST-based tool for calculating WER and aligning two transcript sequences.
functorch - functorch is JAX-like composable function transforms for PyTorch.
ovos-stt-plugin-vosk - vosk STT plugin for mycroft
athena - an open-source implementation of sequence-to-sequence based speech processing engine