GGitHubDifferent accelerators can be called according to specific device conditions (#859)

48177db7创建于 2024年2月10日历史提交

文件	最后提交记录	最后更新时间
README.md	Refactor HuggingFace Inference Examples (#204) This PR reorganizes and refactors the DeepSpeed huggingface inference examples. Changes in this PR: - Remove Transformers folder - Add README(s) - pip install requirements.txt - Code example - Point to benchmarking and other resources in DeepSpeed repo - Normalize all names i.e. test-[model_name].py - Add T5 translation task (English to French) - Add huggingface pipeline() object and refactor test-gptj.py - Create folders for different types of ML tasks (text-generation, fill-mask, etc) - Add BERT fill-mask example - Update queries to something more sensible - TODO: Add test-bloom to text-generation folder - Fix typos in code comments Co-authored-by: Lev Kurilenko <lekurile@microsoft.com> Co-authored-by: Ammar Ahmad Awan <ammar.awan@microsoft.com>	3 年前
requirements.txt	Refactor HuggingFace Inference Examples (#204) This PR reorganizes and refactors the DeepSpeed huggingface inference examples. Changes in this PR: - Remove Transformers folder - Add README(s) - pip install requirements.txt - Code example - Point to benchmarking and other resources in DeepSpeed repo - Normalize all names i.e. test-[model_name].py - Add T5 translation task (English to French) - Add huggingface pipeline() object and refactor test-gptj.py - Create folders for different types of ML tasks (text-generation, fill-mask, etc) - Add BERT fill-mask example - Update queries to something more sensible - TODO: Add test-bloom to text-generation folder - Fix typos in code comments Co-authored-by: Lev Kurilenko <lekurile@microsoft.com> Co-authored-by: Ammar Ahmad Awan <ammar.awan@microsoft.com>	3 年前
test-wav2vec2.py	Different accelerators can be called according to specific device conditions (#859) * test xpu in local * use get_accelerator() to get device * delete load_from_disk --------- Co-authored-by: Olatunji Ruwase <olruwase@microsoft.com> Co-authored-by: Michael Wyatt <mrwyattii@gmail.com>	2 年前

DeepSpeed Huggingface Automatic Speech Recognition Examples

Setup

Python dependencies:

pip install -r requirements.txt

For the test-wav2vec.py speech model example, you may also need to install the libsndfile1-dev generic library:

sudo apt-get install libsndfile1-dev

Usage

Examples can be run as follows:

deepspeed --num_gpus [number of GPUs] test-[model].py

Example Output

Command:

deepspeed --num_gpus 1 test-wav2vec2.py

Output:

WER: 0.03383673158855752