bark

Bark

In this directory, you will find examples on how you could use BigDL-LLM optimize_model API to accelerate Bark models. For illustration purposes, we utilize the suno/bark-small as reference Bark models.

Requirements

To run these examples with BigDL-LLM, we have some recommended requirements for your machine, please refer to here for more information.

Example: Synthesize speech with the given input text

In the example synthesize_speech.py, we show a basic use case for Bark model to synthesize speech based on the given text, with BigDL-LLM INT4 optimizations.

1. Install

1.1 Installation on Linux

We suggest using conda to manage the Python environment. For more information about conda installation, please refer to here.

After installing conda, create a Python environment for BigDL-LLM:

conda create -n llm python=3.9 # recommend to use Python 3.9
conda activate llm

# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
pip install scipy

1.2 Installation on Windows

We suggest using conda to manage environment:

conda create -n llm python=3.9 libuv
conda activate llm

# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
pip install scipy

2. Configures OneAPI environment variables

2.1 Configurations for Linux

source /opt/intel/oneapi/setvars.sh

2.2 Configurations for Windows

call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat"

Note: Please make sure you are using CMD (Anaconda Prompt if using conda) to run the command as PowerShell is not supported.

3. Runtime Configurations

For optimal performance, it is recommended to set several environment variables. Please check out the suggestions based on your device.

3.1 Configurations for Linux

For Intel Arc™ A-Series Graphics and Intel Data Center GPU Flex Series

export USE_XETLA=OFF
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1

For Intel Data Center GPU Max Series

export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
export ENABLE_SDP_FUSION=1

Note: Please note that libtcmalloc.so can be installed by conda install -c conda-forge -y gperftools=2.10.

3.2 Configurations for Windows

For Intel iGPU

set SYCL_CACHE_PERSISTENT=1
set BIGDL_LLM_XMX_DISABLED=1

For Intel Arc™ A300-Series or Pro A60

set SYCL_CACHE_PERSISTENT=1

For other Intel dGPU Series

There is no need to set further environment variables.

Note: For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.

4. Running examples

python ./synthesize_speech.py --text 'BigDL-LLM is a library for running large language model on Intel XPU with very low latency.'

In the example, several arguments can be passed to satisfy your requirements:

• --repo-id-or-model-path REPO_ID_OR_MODEL_PATH: argument defining the huggingface repo id for the Bark model (e.g. suno/bark-small and suno/bark) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'suno/bark-small'.
• --voice-preset: argument defining the voice preset of model. It is default to be 'v2/en_speaker_6'.
• --text TEXT: argument defining the text to synthesize speech. It is default to be "BigDL-LLM is a library for running large language model on Intel XPU with very low latency.".

4.1 Sample Output

suno/bark-small

Text: BigDL-LLM is a library for running large language model on Intel XPU with very low latency.

Click here to hear sample output.