Skip to content

Commit

Permalink
[doc] move install to docs folder (wenet-e2e#1730)
Browse files Browse the repository at this point in the history
  • Loading branch information
robin1001 authored Mar 10, 2023
1 parent 6ad405b commit 8c9ac74
Show file tree
Hide file tree
Showing 2 changed files with 45 additions and 35 deletions.
37 changes: 2 additions & 35 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -39,42 +39,9 @@ to reduce the effort of productionizing E2E models, and to explore better E2E mo

Please see `examples/$dataset/s0/README.md` for benchmark on different speech datasets.

## Installation(Python Only)
## Install
please refer [doc](docs/install.md) for install.

If you just want to use WeNet as a python package for speech recognition application,
just install it by `pip`, please note python 3.6+ is required.
``` sh
pip3 install wenetruntime
```

And please see [doc](runtime/binding/python/README.md) for usage.


## Installation(Training and Developing)

- Clone the repo
``` sh
git clone https://github.com/wenet-e2e/wenet.git
```

- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
- Create Conda env:

``` sh
conda create -n wenet python=3.8
conda activate wenet
pip install -r requirements.txt
conda install pytorch=1.10.0 torchvision torchaudio=0.10.0 cudatoolkit=11.1 -c pytorch -c conda-forge
```

- Optionally, if you want to use x86 runtime or language model(LM),
you have to build the runtime as follows. Otherwise, you can just ignore this step.

``` sh
# runtime build requires cmake 3.14 or above
cd runtime/libtorch
mkdir build && cd build && cmake -DGRAPH_TOOLS=ON .. && cmake --build .
```

## Discussion & Communication

Expand Down
43 changes: 43 additions & 0 deletions docs/install.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
# Install

## Install prebuilt python package

If you just want to use WeNet as a python package for speech recognition application,
just install it by `pip`, please note python 3.6+ is required.
``` sh
pip3 install wenetruntime
```

And please see [doc](https://github.com/wenet-e2e/wenet/tree/main/runtime/binding/python) for usage.


## Install for training

- Clone the repo
``` sh
git clone https://github.com/wenet-e2e/wenet.git
```

- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
- Create Conda env:

``` sh
conda create -n wenet python=3.8
conda activate wenet
pip install -r requirements.txt
conda install pytorch=1.10.0 torchvision torchaudio=0.10.0 cudatoolkit=11.1 -c pytorch -c conda-forge
```

## Build for deployment

Optionally, if you want to use x86 runtime or language model(LM),
you have to build the runtime as follows. Otherwise, you can just ignore this step.

``` sh
# runtime build requires cmake 3.14 or above
cd runtime/libtorch
mkdir build && cd build && cmake -DGRAPH_TOOLS=ON .. && cmake --build .
```

Please see [doc](https://github.com/wenet-e2e/wenet/tree/main/runtime) for building
runtime on more platforms and OS.

0 comments on commit 8c9ac74

Please sign in to comment.