%global _empty_manifest_terminate_build 0 Name: python-speechmix Version: 0.0.32 Release: 1 Summary: Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together License: Apache URL: https://github.com/voidful/SpeechMix Source0: https://mirrors.nju.edu.cn/pypi/web/packages/04/e0/8453be39c4d6e137addaa530d3074ff8de2111a826dc82d88df46b4942a7/speechmix-0.0.32.tar.gz BuildArch: noarch Requires: python3-asrp Requires: python3-transformers Requires: python3-datasets Requires: python3-librosa Requires: python3-s3prl %description # SpeechMix Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together. Implementation of: [Large-Scale Self- and Semi-Supervised Learning for Speech Translation](https://arxiv.org/abs/2104.06678) - ACL2021 [Multilingual Speech Translation with Efficient Finetuning of Pretrained Models](https://arxiv.org/abs/2010.12829) - ACL2021 [Lightweight Adapter Tuning for Multilingual Speech Translation](https://arxiv.org/abs/2106.01463) - Interspeech 2021 [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://arxiv.org/abs/2107.05782) - ACL2021 [A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks](https://arxiv.org/abs/2010.11338) - ICASSP 2021 ## Installation ### pip install ```bash pip install speechmix ``` ### Build from source git clone and cd into this project. ```shell pip install -e . ``` ## Name the project(!important) WANDB_PROJECT=amazing ## base ```shell python train.py --speech_model_config wav2vec2 \ --nlp_model_config facebook/bart-base \ --SpeechMixEED \ --dataset librispeech_asr \ --field clean \ --train_split train.100 \ --test_split validation \ --batch 3 \ --grad_accum 20 \ --epoch 30 \ --worker 15 \ --share_layer_ratio 0 \ --down_scale 2 \ --lr 4e-5 \ --warmup_steps 500 \ --wandb \ --notes base ``` %package -n python3-speechmix Summary: Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together Provides: python-speechmix BuildRequires: python3-devel BuildRequires: python3-setuptools BuildRequires: python3-pip %description -n python3-speechmix # SpeechMix Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together. Implementation of: [Large-Scale Self- and Semi-Supervised Learning for Speech Translation](https://arxiv.org/abs/2104.06678) - ACL2021 [Multilingual Speech Translation with Efficient Finetuning of Pretrained Models](https://arxiv.org/abs/2010.12829) - ACL2021 [Lightweight Adapter Tuning for Multilingual Speech Translation](https://arxiv.org/abs/2106.01463) - Interspeech 2021 [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://arxiv.org/abs/2107.05782) - ACL2021 [A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks](https://arxiv.org/abs/2010.11338) - ICASSP 2021 ## Installation ### pip install ```bash pip install speechmix ``` ### Build from source git clone and cd into this project. ```shell pip install -e . ``` ## Name the project(!important) WANDB_PROJECT=amazing ## base ```shell python train.py --speech_model_config wav2vec2 \ --nlp_model_config facebook/bart-base \ --SpeechMixEED \ --dataset librispeech_asr \ --field clean \ --train_split train.100 \ --test_split validation \ --batch 3 \ --grad_accum 20 \ --epoch 30 \ --worker 15 \ --share_layer_ratio 0 \ --down_scale 2 \ --lr 4e-5 \ --warmup_steps 500 \ --wandb \ --notes base ``` %package help Summary: Development documents and examples for speechmix Provides: python3-speechmix-doc %description help # SpeechMix Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together. Implementation of: [Large-Scale Self- and Semi-Supervised Learning for Speech Translation](https://arxiv.org/abs/2104.06678) - ACL2021 [Multilingual Speech Translation with Efficient Finetuning of Pretrained Models](https://arxiv.org/abs/2010.12829) - ACL2021 [Lightweight Adapter Tuning for Multilingual Speech Translation](https://arxiv.org/abs/2106.01463) - Interspeech 2021 [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://arxiv.org/abs/2107.05782) - ACL2021 [A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks](https://arxiv.org/abs/2010.11338) - ICASSP 2021 ## Installation ### pip install ```bash pip install speechmix ``` ### Build from source git clone and cd into this project. ```shell pip install -e . ``` ## Name the project(!important) WANDB_PROJECT=amazing ## base ```shell python train.py --speech_model_config wav2vec2 \ --nlp_model_config facebook/bart-base \ --SpeechMixEED \ --dataset librispeech_asr \ --field clean \ --train_split train.100 \ --test_split validation \ --batch 3 \ --grad_accum 20 \ --epoch 30 \ --worker 15 \ --share_layer_ratio 0 \ --down_scale 2 \ --lr 4e-5 \ --warmup_steps 500 \ --wandb \ --notes base ``` %prep %autosetup -n speechmix-0.0.32 %build %py3_build %install %py3_install install -d -m755 %{buildroot}/%{_pkgdocdir} if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi pushd %{buildroot} if [ -d usr/lib ]; then find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst fi if [ -d usr/lib64 ]; then find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst fi if [ -d usr/bin ]; then find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst fi if [ -d usr/sbin ]; then find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst fi touch doclist.lst if [ -d usr/share/man ]; then find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst fi popd mv %{buildroot}/filelist.lst . mv %{buildroot}/doclist.lst . %files -n python3-speechmix -f filelist.lst %dir %{python3_sitelib}/* %files help -f doclist.lst %{_docdir}/* %changelog * Tue Apr 25 2023 Python_Bot - 0.0.32-1 - Package Spec generated