Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-24 22:45:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Dockerfile.hpu and README.md files:

Browse Source 
- rename `requirements_hpu.txt`,
- make docker run mapping optional,
- add running HPU tests in docs
This commit is contained in:
PiotrBLL 2024-11-12 20:36:09 +01:00
parent 3e826a2aff
commit 6770610528
2 changed files with 30 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Dockerfile.hpu
View File

@ -23,13 +23,12 @@ RUN mkdir -p /usr/local/bin/ffmpeg && \
cp -a ffmpeg-*-static/ffprobe /usr/bin/ffprobe && \
rm -rf /usr/local/bin/ffmpeg
# Add Whisper repo contents
ADD . /root/whisper
WORKDIR /root/whisper
COPY . /workspace/whisper
WORKDIR /workspace/whisper
# Copy HPU requirements
COPY requirements_hpu.txt /root/whisper/requirements.txt
COPY requirements_hpu.txt /workspace/requirements_hpu.txt
# Install Python packages
RUN pip install --upgrade pip \
&& pip install -r requirements.txt
&& pip install -r requirements_hpu.txt

31
README.md
View File

@ -93,6 +93,10 @@ Adding `--task translate` will translate the speech into English:
whisper japanese.wav --language Japanese --task translate
The following command will transcribe speech in audio files, using the Intel® Gaudi® HPU (`--device hpu` option):
whisper audio.flac audio.mp3 audio.wav --model turbo --device hpu
Run the following to view all available options:
whisper --help
@ -148,23 +152,40 @@ print(result.text)
docker build -t whisper_hpu:latest -f Dockerfile.hpu .
```
In the `Dockerfile.hpu`, we use the `vault.habana.ai/gaudi-docker/1.17.0/ubuntu22.04/habanalabs/pytorch-installer-2.3.1:latest` base image, make sure to replace it with the appropriate version for your environment if needed.
In the `Dockerfile.hpu`, we use the `vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.3.1:latest` base image, make sure to replace it with the appropriate version for your environment if needed.
See the [PyTorch Docker Images for the Intel® Gaudi® Accelerator](https://developer.habana.ai/catalog/pytorch-container/) for more information.
### Run the Container
```bash
docker run -it --runtime=habana -v /path/to/your/whisper:/root/whisper whisper_hpu:latest /bin/bash
docker run -it --runtime=habana whisper_hpu:latest
```
Make sure to replace `/path/to/your/whisper` with the path to the Whisper repository on your local machine.
Using a mapping volume (`-v`) is optional, but it allows you to access the Whisper repository from within the container.
You can make this by adding `-v /path/to/your/whisper:/workspace/whisper` to the `docker run` command.
If you decide to use the mapping make sure to replace `/path/to/your/whisper` with the path to the Whisper repository on your local machine.
### Command-line usage with Intel® Gaudi® hpu
To run the `whisper` command with Intel® Gaudi® hpu, you can use the `--device hpu` option:
To run the `transcribe` process with Intel® Gaudi® HPU, you can use the `--device hpu` option:
python3 -m whisper.transcribe audio.flac audio.mp3 audio.wav --model turbo --device hpu
```bash
python3 -m whisper.transcribe audio_file.wav --model turbo --device hpu
```
* Note: Change `audio_file.wav` to the path of the audio file you want to transcribe. (Example file: https://www.kaggle.com/datasets/pavanelisetty/sample-audio-files-for-speech-recognition?resource=download)
To run the `transcribe` tests with Intel® Gaudi® HPU, make sure to install the `pytest` package:
```bash
pip install pytest
```
and run the following command:
```bash
PYTHONPATH=. pytest -s tests/test_transcribe.py::test_transcribe_hpu
```
### Python usage with Intel® Gaudi® hpu