{"id":19544670,"url":"https://github.com/viig99/esolafast","last_synced_at":"2025-04-26T18:31:44.296Z","repository":{"id":41490189,"uuid":"279334384","full_name":"viig99/esolafast","owner":"viig99","description":"Fast C++ implementation of ESOLA using KFRLib, can be used for online time-stretch augmentation during SpeechToText training.","archived":false,"fork":false,"pushed_at":"2020-07-25T19:16:31.000Z","size":32,"stargazers_count":15,"open_issues_count":0,"forks_count":2,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-04T17:04:20.824Z","etag":null,"topics":["asr","esola","kfr","pybind11","python-bindings","speech","speech-augmentation","speech-processing","speech-recognition","speech-to-text","time-stretch"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/viig99.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-07-13T15:01:24.000Z","updated_at":"2024-07-24T13:32:35.000Z","dependencies_parsed_at":"2022-08-28T19:15:03.539Z","dependency_job_id":null,"html_url":"https://github.com/viig99/esolafast","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viig99%2Fesolafast","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viig99%2Fesolafast/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viig99%2Fesolafast/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viig99%2Fesolafast/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/viig99","download_url":"https://codeload.github.com/viig99/esolafast/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251035741,"owners_count":21526417,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["asr","esola","kfr","pybind11","python-bindings","speech","speech-augmentation","speech-processing","speech-recognition","speech-to-text","time-stretch"],"created_at":"2024-11-11T03:30:38.883Z","updated_at":"2025-04-26T18:31:39.287Z","avatar_url":"https://github.com/viig99.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Epoch-Synchronous Overlap-Add (ESOLA) \nFast C++ implementation of ESOLA using KFRLib, can be used for online time-stretch augmentation during SpeechToText training.\n\n## C++ Rewrite\nMostly an C++ re-write of https://github.com/BaronVladziu/ESOLA-Implementation to be used in Online SpeechToText training.\n\n## Build\n```$xslt\n    git clone https://github.com/viig99/esolafast.git\n    cd esolafast\n    git submodule update --init --recursive\n    mkdir build \u0026\u0026 cd build\n    cmake ..\n    make -j`nproc`\n```\n\n## Run\n```$xslt\n    ./esolafast -i INPUT_PATH -o OUTPUT_PATH -t 1.5\n    ./esolafast --help\n```\n\n## Performance\nRight now faster than sox, sound-stretch \u0026 rubberband, CPU usage is much higher. Quality is better than rubberband, same as sox \u0026 sound-stretch.\n```$xslt\n$ time sox sample_file.wav sox_1_5.wav tempo 1.5\nsox sox_1_5.wav tempo 2.0  0.01s user 0.01s system 17% cpu 0.022 total\n\n$ time soundstretch sample_file.wav st_1_5.wav -tempo=1.5\nsoundstretch st_1_5.wav -tempo=1.5  0.01s user 0.00s system 44% cpu 0.022 total\n\n$ time esolafast -i sample_file.wav -o es_1_5.wav -t 1.5\nesolafast -i  -o  -t 1.5  0.01s user 0.00s system 92% cpu 0.010 total\n\n$ time rubberband -q -T 1.5 sample_file.wav rb_1_5.wav\nrubberband -q -T 1.5  rb_1_5.wav  0.01s user 0.00s system 89% cpu 0.022 total\n```\n\n## Python Bindings\nGenerate the python bindings, using pybind11\n```asm\n $ python setup.py build\n```\n\nFor example using the python binding check `examples/test.py`\n\n## References\n* [Epoch-Synchronous Overlap-Add (ESOLA) for Time- and Pitch-Scale Modification of Speech Signals\n](https://arxiv.org/abs/1801.06492)\n* [Epoch Extraction From Speech Signals](https://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=6D94C490DA889017DE4362D322E1A23C?doi=10.1.1.586.7214\u0026rep=rep1\u0026type=pdf)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fviig99%2Fesolafast","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fviig99%2Fesolafast","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fviig99%2Fesolafast/lists"}