wav2letter | Facebook AI Research 's Automatic Speech Recognition Toolkit | Speech library

by facebookresearch Python Version: v0.1 License: Non-SPDX

X-Ray Key Features Code Snippets(3)Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | wav2letter Summary

wav2letter is a Python library typically used in Artificial Intelligence, Speech, Deep Learning, Pytorch applications. wav2letter has no bugs, it has no vulnerabilities and it has medium support. However wav2letter build file is not available and it has a Non-SPDX License. You can download it from GitHub.

wav2letter++ is a highly efficient end-to-end automatic speech recognition (ASR) toolkit written entirely in C++, leveraging ArrayFire and flashlight. The toolkit started from models predicting letters directly from the raw waveform, and now evolved as an all-purpose end-to-end ASR research toolkit, supporting a wide range of models and learning techniques. It also embarks a very efficient modular beam-search decoder, for both structured learning (CTC, ASG) and seq2seq approaches. Important disclaimer: as a number of models from this repository could be used for other modalities, we moved most of the code to flashlight.

Support

Quality

Security

License

Reuse

Support

wav2letter has a medium active ecosystem.

It has 5531 star(s) with 932 fork(s). There are 249 watchers for this library.

It had no major release in the last 12 months.

There are 94 open issues and 754 have been closed. On average issues are closed in 113 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of wav2letter is v0.1

Quality

wav2letter has 0 bugs and 0 code smells.

Security

wav2letter has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

wav2letter code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

wav2letter has a Non-SPDX License.

Non-SPDX licenses can be open source with a non SPDX compliant license, or non open source licenses, and you need to review them closely before use.

Reuse

wav2letter releases are available to install and integrate.

wav2letter has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions, examples and code snippets are available.

Top functions reviewed by kandi - BETA

kandi's functional review helps you automatically verify the functionalities of the libraries and avoid rework.
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of wav2letter

Get all kandi verified functions for this library.

wav2letter Key Features

No Key Features are available at this moment for wav2letter.

wav2letter Examples and Code Snippets

Example

Python

Lines of Code : 21

License : No License

Copy

# download the pretrained model weights for English and Russian
wget https://github.com/vadimkantorov/inferspeech/releases/download/pretrained/w2l_plus_large_mp.h5 # English, Wav2Letter
wget https://github.com/vadimkantorov/inferspeech/releases/downl

Browser demo with TensorFlow.js (work in progress)

Python

Lines of Code : 8

License : No License

Copy

# download and extract the exported tfjs model
wget https://github.com/vadimkantorov/inferspeech/releases/download/pretrained/w2l_plus_large_mp.tfjs.tar.gz
tar -xf w2l_plus_large_mp.tfjs.tar.gz

# serve the tfjs model and demo.html file
python3 -m ht

wav2vec,Alternative install

Python

Lines of Code : 4

License : Permissive (MIT)

Copy

docker build -t wav2vec2 -f wav2letter.Dockerfile .
docker run -d -it --rm -v $PWD/data:/root/data --name w2v2 wav2vec2
docker exec -it w2v2 bash
python examples/wav2vec/recognize.py --wav_path /root/data/temp.wav --w2v_path /root/data/wav2vec_small_

Community Discussions

Trending Discussions on wav2letter

Using C++ Libraries on Linux

QUESTION

Using C++ Libraries on Linux

Asked 2021-Dec-22 at 04:31

I'm trying to follow along here to use a speech recognition model. The model is in C++, and almost all of my experience is in Python.

I installed a virtual machine running Ubuntu, and still the installation procedure was failing for me. I decided to simply try to compile the model so that I could call it in a Python script, as seen at the bottom of the linked page.

I'm trying to use g++ to compile the .cpp model, but I keep getting an error saying that a library that I have installed is not found:

...

ANSWER

Answered 2021-Dec-22 at 04:31

You've installed only the runtime libraries. You also have to install the development version (e.g. header files), most likely called something like cereal-devel or so.

Alan Birtles provided a link to the development packages in the comments section above.

https://packages.ubuntu.com/focal/libcereal-dev

Source https://stackoverflow.com/questions/70440025

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install wav2letter

First, isntall flashlight with all its dependencies. Then. If flashlight or ArrayFire are installed in nonstandard paths via CMAKE_INSTALL_PREFIX, they can be found by passing -Dflashlight_DIR=[PREFIX]/usr/share/flashlight/cmake/ -DArrayFire_DIR=[PREFIX]/usr/share/ArrayFire/cmake when running cmake.