{"id":18084,"name":"nemo_voicetextblender","description":"NAACL 2025 main conference: \"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning\"","url":"https://github.com/pyf98/nemo_voicetextblender","last_synced_at":"2025-09-04T23:48:23.409Z","repository":{"id":276226474,"uuid":"928634618","full_name":"pyf98/NeMo_VoiceTextBlender","owner":"pyf98","description":"NAACL 2025 main conference: \"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning\"","archived":false,"fork":false,"pushed_at":"2025-04-27T17:19:55.000Z","size":154345,"stargazers_count":8,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"speechllm-develop-yifanp","last_synced_at":"2025-04-27T17:37:59.591Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pyf98.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-02-07T00:44:03.000Z","updated_at":"2025-04-27T17:19:58.000Z","dependencies_parsed_at":"2025-04-12T15:10:46.784Z","dependency_job_id":null,"html_url":"https://github.com/pyf98/NeMo_VoiceTextBlender","commit_stats":null,"previous_names":["pyf98/nemo_voicetextblender"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pyf98/NeMo_VoiceTextBlender","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2FNeMo_VoiceTextBlender","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2FNeMo_VoiceTextBlender/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2FNeMo_VoiceTextBlender/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2FNeMo_VoiceTextBlender/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pyf98","download_url":"https://codeload.github.com/pyf98/NeMo_VoiceTextBlender/tar.gz/refs/heads/speechllm-develop-yifanp","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2FNeMo_VoiceTextBlender/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273690297,"owners_count":25150630,"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","status":"online","status_checked_at":"2025-09-04T02:00:08.968Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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"}},"owner":{"login":"pyf98","name":"Yifan Peng","uuid":"29177009","kind":"user","description":"Speech Recognition | Ph.D. Candidate at CMU | B.E. from Tsinghua EE","email":"","website":"https://pyf98.github.io","location":"Pittsburgh, PA","twitter":null,"company":"Carnegie Mellon University","icon_url":"https://avatars.githubusercontent.com/u/29177009?u=08532490efee408450485c6ab49560f7857e38c3\u0026v=4","repositories_count":3,"last_synced_at":"2023-03-05T04:59:26.355Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/pyf98","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-15T06:21:48.851Z","updated_at":"2023-03-05T04:59:26.362Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pyf98","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pyf98/repositories"},"packages":[],"commits":{"id":8758265,"full_name":"pyf98/nemo_voicetextblender","default_branch":"master","committers":null,"total_commits":null,"total_committers":null,"total_bot_commits":null,"total_bot_committers":null,"mean_commits":null,"dds":null,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":null,"last_synced_commit":null,"created_at":"2025-02-14T16:59:25.789Z","updated_at":"2025-02-14T16:59:25.789Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2Fnemo_voicetextblender/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.936Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"pyf98/nemo_voicetextblender","html_url":"https://github.com/pyf98/nemo_voicetextblender","last_synced_at":"2025-04-08T21:44:15.964Z","status":null,"issues_count":0,"pull_requests_count":0,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":0,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":0,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2025-02-14T16:59:25.940Z","updated_at":"2025-08-31T02:02:15.342Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2Fnemo_voicetextblender","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/pyf98%2Fnemo_voicetextblender/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":2},"pull_request_author_associations_count":{},"issue_authors":{"sankar-mukherjee":1,"Sangkikim-77":1},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10082405,"issues_count":31230170,"pull_requests_count":96100294,"authors_count":10694153,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{"NONE":2},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{"Sangkikim-77":1,"sankar-mukherjee":1},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"IssuesEvent":3,"WatchEvent":7,"IssueCommentEvent":4,"PushEvent":19,"ForkEvent":2,"CreateEvent":2},"last_year":{"IssuesEvent":3,"WatchEvent":7,"IssueCommentEvent":4,"PushEvent":19,"ForkEvent":2,"CreateEvent":2}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/actions/cancel-workflow/action.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:30.438Z","updated_at":"2025-02-07T01:42:30.438Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/actions/cancel-workflow/action.yml","dependencies":[]},{"ecosystem":"actions","filepath":".github/workflows/_test_template.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:30.485Z","updated_at":"2025-02-07T01:42:30.485Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/_test_template.yml","dependencies":[{"id":21773638227,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21773638228,"package_name":"NVIDIA/NeMo/.github/actions/cancel-workflow","ecosystem":"actions","requirements":"main","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/changelog-build.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:30.758Z","updated_at":"2025-02-07T01:42:30.758Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/changelog-build.yml","dependencies":[{"id":21773638229,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":21773638230,"package_name":"mikepenz/release-changelog-builder-action","ecosystem":"actions","requirements":"v3.3.1","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/cherry-pick-release-commit.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:30.843Z","updated_at":"2025-02-07T01:42:30.843Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/cherry-pick-release-commit.yml","dependencies":[{"id":21773638231,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":21773638232,"package_name":"carloscastrojumo/github-cherry-pick-action","ecosystem":"actions","requirements":"bb0869df47c27be4ae4c7a2d93d22827aa5a0054","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/cicd-main.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:31.952Z","updated_at":"2025-02-07T01:42:31.952Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/cicd-main.yml","dependencies":[{"id":21773638354,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21773638355,"package_name":"docker/setup-buildx-action","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":21773638356,"package_name":"docker/build-push-action","ecosystem":"actions","requirements":"v5","direct":true,"kind":"composite","optional":false},{"id":21773638357,"package_name":"NVIDIA/NeMo/.github/actions/cancel-workflow","ecosystem":"actions","requirements":"main","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/close-inactive-issue-pr.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:32.026Z","updated_at":"2025-02-07T01:42:32.026Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/close-inactive-issue-pr.yml","dependencies":[{"id":21773638366,"package_name":"actions/stale","ecosystem":"actions","requirements":"v6","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/code-formatting.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:32.322Z","updated_at":"2025-02-07T01:42:32.322Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/code-formatting.yml","dependencies":[{"id":21773638400,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21773638401,"package_name":"tj-actions/changed-files","ecosystem":"actions","requirements":"v44","direct":true,"kind":"composite","optional":false},{"id":21773638402,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v5","direct":true,"kind":"composite","optional":false},{"id":21773638403,"package_name":"psf/black","ecosystem":"actions","requirements":"stable","direct":true,"kind":"composite","optional":false},{"id":21773638404,"package_name":"isort/isort-action","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":21773638405,"package_name":"EndBug/add-and-commit","ecosystem":"actions","requirements":"v9","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/codeql.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:33.976Z","updated_at":"2025-02-07T01:42:33.976Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/codeql.yml","dependencies":[{"id":21773638406,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":21773638407,"package_name":"github/codeql-action/init","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":21773638408,"package_name":"github/codeql-action/autobuild","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":21773638409,"package_name":"github/codeql-action/analyze","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/config/codeql.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:34.275Z","updated_at":"2025-02-07T01:42:34.275Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/config/codeql.yml","dependencies":[]},{"ecosystem":"actions","filepath":".github/workflows/gh-docs.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:34.335Z","updated_at":"2025-02-07T01:42:34.335Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/gh-docs.yml","dependencies":[{"id":21773638410,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/import-test.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:34.404Z","updated_at":"2025-02-07T01:42:34.404Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/import-test.yml","dependencies":[{"id":21773638411,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/labeler.yml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:34.475Z","updated_at":"2025-02-07T01:42:34.475Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/.github/workflows/labeler.yml","dependencies":[{"id":21773638412,"package_name":"actions/labeler","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"docker","filepath":"Dockerfile","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:34.546Z","updated_at":"2025-02-07T01:42:34.546Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/Dockerfile","dependencies":[{"id":21773638413,"package_name":"${BASE_IMAGE}","ecosystem":"docker","requirements":"latest","direct":true,"kind":"build","optional":false},{"id":21773638414,"package_name":"scratch","ecosystem":"docker","requirements":"latest","direct":true,"kind":"build","optional":false},{"id":21773638415,"package_name":"nemo-deps","ecosystem":"docker","requirements":"latest","direct":true,"kind":"build","optional":false}]},{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:37.075Z","updated_at":"2025-02-07T01:42:37.075Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/pyproject.toml","dependencies":[]},{"ecosystem":"pypi","filepath":"requirements/requirements.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:37.122Z","updated_at":"2025-02-07T01:42:37.122Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements.txt","dependencies":[{"id":21773638416,"package_name":"fiddle","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638427,"package_name":"huggingface_hub","ecosystem":"pypi","requirements":"\u003e=0.20.3","direct":true,"kind":"runtime","optional":false},{"id":21773638428,"package_name":"numba","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638429,"package_name":"numpy","ecosystem":"pypi","requirements":"\u003e=1.22","direct":true,"kind":"runtime","optional":false},{"id":21773638430,"package_name":"onnx","ecosystem":"pypi","requirements":"\u003e=1.7.0","direct":true,"kind":"runtime","optional":false},{"id":21773638431,"package_name":"python-dateutil","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638432,"package_name":"ruamel.yaml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638433,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638434,"package_name":"setuptools","ecosystem":"pypi","requirements":"\u003e=65.5.1","direct":true,"kind":"runtime","optional":false},{"id":21773638435,"package_name":"tensorboard","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638436,"package_name":"text-unidecode","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638437,"package_name":"torch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638438,"package_name":"tqdm","ecosystem":"pypi","requirements":"\u003e=4.41.0","direct":true,"kind":"runtime","optional":false},{"id":21773638439,"package_name":"wget","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638440,"package_name":"wrapt","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_asr.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:38.763Z","updated_at":"2025-02-07T01:42:38.763Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_asr.txt","dependencies":[{"id":21773638441,"package_name":"braceexpand","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638442,"package_name":"editdistance","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638443,"package_name":"einops","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638444,"package_name":"g2p_en","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638445,"package_name":"ipywidgets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638446,"package_name":"jiwer","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638447,"package_name":"kaldi-python-io","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638448,"package_name":"kaldiio","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638449,"package_name":"lhotse","ecosystem":"pypi","requirements":"\u003e=1.22.0","direct":true,"kind":"runtime","optional":false},{"id":21773638450,"package_name":"librosa","ecosystem":"pypi","requirements":"\u003e=0.10.0","direct":true,"kind":"runtime","optional":false},{"id":21773638451,"package_name":"marshmallow","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638452,"package_name":"matplotlib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638453,"package_name":"packaging","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638454,"package_name":"pyannote.core","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638455,"package_name":"pyannote.metrics","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638456,"package_name":"pydub","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638457,"package_name":"pyloudnorm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638458,"package_name":"resampy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638459,"package_name":"ruamel.yaml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638460,"package_name":"scipy","ecosystem":"pypi","requirements":"\u003e=0.14","direct":true,"kind":"runtime","optional":false},{"id":21773638461,"package_name":"soundfile","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638462,"package_name":"sox","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638463,"package_name":"texterrors","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_common.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:41.965Z","updated_at":"2025-02-07T01:42:41.965Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_common.txt","dependencies":[{"id":21773638464,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638465,"package_name":"inflect","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638466,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638467,"package_name":"sacremoses","ecosystem":"pypi","requirements":"\u003e=0.0.43","direct":true,"kind":"runtime","optional":false},{"id":21773638468,"package_name":"sentencepiece","ecosystem":"pypi","requirements":"\u003c1.0.0","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_docs.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:42.229Z","updated_at":"2025-02-07T01:42:42.229Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_docs.txt","dependencies":[{"id":21773638469,"package_name":"boto3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638470,"package_name":"Jinja2","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638471,"package_name":"latexcodec","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638472,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638473,"package_name":"pydata-sphinx-theme","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638474,"package_name":"Sphinx","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638475,"package_name":"sphinx-book-theme","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638476,"package_name":"sphinx-copybutton","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638477,"package_name":"sphinxcontrib-bibtex","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638478,"package_name":"sphinxext-opengraph","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638479,"package_name":"urllib3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638480,"package_name":"wrapt","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_infer.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:43.249Z","updated_at":"2025-02-07T01:42:43.249Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_infer.txt","dependencies":[{"id":21773638481,"package_name":"nvidia-pytriton","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638482,"package_name":"tensorstore","ecosystem":"pypi","requirements":"==0.1.45","direct":true,"kind":"runtime","optional":false},{"id":21773638483,"package_name":"zarr","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_lightning.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:43.389Z","updated_at":"2025-02-07T01:42:43.389Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_lightning.txt","dependencies":[{"id":21773638484,"package_name":"cloudpickle","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638485,"package_name":"fiddle","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638486,"package_name":"hydra-core","ecosystem":"pypi","requirements":"\u003e1.3,\u003c=1.3.2","direct":true,"kind":"runtime","optional":false},{"id":21773638487,"package_name":"omegaconf","ecosystem":"pypi","requirements":"\u003c=2.3","direct":true,"kind":"runtime","optional":false},{"id":21773638488,"package_name":"pytorch-lightning","ecosystem":"pypi","requirements":"\u003e=2.2.1","direct":true,"kind":"runtime","optional":false},{"id":21773638489,"package_name":"torchmetrics","ecosystem":"pypi","requirements":"\u003e=0.11.0","direct":true,"kind":"runtime","optional":false},{"id":21773638490,"package_name":"transformers","ecosystem":"pypi","requirements":"\u003e=4.36.0,\u003c=4.40.2","direct":true,"kind":"runtime","optional":false},{"id":21773638491,"package_name":"wandb","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638492,"package_name":"webdataset","ecosystem":"pypi","requirements":"\u003e=0.2.86","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_multimodal.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:43.897Z","updated_at":"2025-02-07T01:42:43.897Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_multimodal.txt","dependencies":[{"id":21773638493,"package_name":"addict","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638494,"package_name":"clip","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638495,"package_name":"decord","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638496,"package_name":"diffusers","ecosystem":"pypi","requirements":"\u003e=0.19.3","direct":true,"kind":"runtime","optional":false},{"id":21773638497,"package_name":"einops_exts","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638498,"package_name":"imageio","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638499,"package_name":"kornia","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638500,"package_name":"nerfacc","ecosystem":"pypi","requirements":"\u003e=0.5.3","direct":true,"kind":"runtime","optional":false},{"id":21773638501,"package_name":"open_clip_torch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638502,"package_name":"PyMCubes","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638503,"package_name":"taming-transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638504,"package_name":"torchdiffeq","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638505,"package_name":"torchsde","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638506,"package_name":"trimesh","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_nlp.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:46.113Z","updated_at":"2025-02-07T01:42:46.113Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_nlp.txt","dependencies":[{"id":21773638507,"package_name":"accelerated-scan","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638508,"package_name":"boto3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638509,"package_name":"causal-conv1d","ecosystem":"pypi","requirements":"==1.2.0.post2","direct":true,"kind":"runtime","optional":false},{"id":21773638510,"package_name":"einops","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638511,"package_name":"faiss-cpu","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638512,"package_name":"fasttext","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638513,"package_name":"flask_restful","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638514,"package_name":"ftfy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638515,"package_name":"gdown","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638516,"package_name":"h5py","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638517,"package_name":"ijson","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638518,"package_name":"jieba","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638519,"package_name":"markdown2","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638520,"package_name":"matplotlib","ecosystem":"pypi","requirements":"\u003e=3.3.2","direct":true,"kind":"runtime","optional":false},{"id":21773638521,"package_name":"nltk","ecosystem":"pypi","requirements":"\u003e=3.6.5","direct":true,"kind":"runtime","optional":false},{"id":21773638522,"package_name":"opencc","ecosystem":"pypi","requirements":"\u003c1.1.7","direct":true,"kind":"runtime","optional":false},{"id":21773638523,"package_name":"pangu","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638524,"package_name":"rapidfuzz","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638525,"package_name":"rouge_score","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638526,"package_name":"sacrebleu","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638527,"package_name":"sentence_transformers","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638528,"package_name":"tensorstore","ecosystem":"pypi","requirements":"\u003c0.1.46","direct":true,"kind":"runtime","optional":false},{"id":21773638529,"package_name":"zarr","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_slu.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:49.521Z","updated_at":"2025-02-07T01:42:49.521Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_slu.txt","dependencies":[{"id":21773638530,"package_name":"jiwer","ecosystem":"pypi","requirements":"\u003e=2.0.0","direct":true,"kind":"runtime","optional":false},{"id":21773638531,"package_name":"progress","ecosystem":"pypi","requirements":"\u003e=1.5","direct":true,"kind":"runtime","optional":false},{"id":21773638532,"package_name":"tabulate","ecosystem":"pypi","requirements":"\u003e=0.8.7","direct":true,"kind":"runtime","optional":false},{"id":21773638533,"package_name":"textdistance","ecosystem":"pypi","requirements":"\u003e=4.1.5","direct":true,"kind":"runtime","optional":false},{"id":21773638534,"package_name":"tqdm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_test.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:50.012Z","updated_at":"2025-02-07T01:42:50.012Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_test.txt","dependencies":[{"id":21773638535,"package_name":"black","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638536,"package_name":"click","ecosystem":"pypi","requirements":"==8.0.2","direct":true,"kind":"test","optional":false},{"id":21773638537,"package_name":"isort","ecosystem":"pypi","requirements":"\u003e5.1.0,\u003c6.0.0","direct":true,"kind":"test","optional":false},{"id":21773638538,"package_name":"parameterized","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638539,"package_name":"pytest","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638540,"package_name":"pytest-mock","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638541,"package_name":"pytest-runner","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638542,"package_name":"ruamel.yaml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638543,"package_name":"sphinx","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638544,"package_name":"sphinxcontrib-bibtex","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638545,"package_name":"wandb","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638546,"package_name":"wget","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false},{"id":21773638547,"package_name":"wrapt","ecosystem":"pypi","requirements":"*","direct":true,"kind":"test","optional":false}]},{"ecosystem":"pypi","filepath":"requirements/requirements_tts.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:50.335Z","updated_at":"2025-02-07T01:42:50.335Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/requirements/requirements_tts.txt","dependencies":[{"id":21773638548,"package_name":"attrdict","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638549,"package_name":"einops","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638550,"package_name":"jieba","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638551,"package_name":"kornia","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638552,"package_name":"librosa","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638553,"package_name":"matplotlib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638554,"package_name":"nemo_text_processing","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638555,"package_name":"nltk","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638556,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638557,"package_name":"pypinyin","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638558,"package_name":"pypinyin-dict","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"scripts/freesound_download_resample/freesound_requirements.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:52.956Z","updated_at":"2025-02-07T01:42:52.956Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/scripts/freesound_download_resample/freesound_requirements.txt","dependencies":[{"id":21773638668,"package_name":"joblib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638672,"package_name":"librosa","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638674,"package_name":"requests","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773638677,"package_name":"requests_oauthlib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639783,"package_name":"sox","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:53.609Z","updated_at":"2025-02-07T01:42:53.609Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/setup.py","dependencies":[]},{"ecosystem":"pypi","filepath":"tools/ctc_segmentation/requirements.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:53.655Z","updated_at":"2025-02-07T01:42:53.655Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/tools/ctc_segmentation/requirements.txt","dependencies":[{"id":21773639802,"package_name":"ctc_segmentation","ecosystem":"pypi","requirements":"==1.7.1","direct":true,"kind":"runtime","optional":false},{"id":21773639817,"package_name":"num2words","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"tools/nemo_forced_aligner/requirements.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:53.798Z","updated_at":"2025-02-07T01:42:53.798Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/tools/nemo_forced_aligner/requirements.txt","dependencies":[{"id":21773639842,"package_name":"nemo_toolkit","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639870,"package_name":"prettyprinter","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639882,"package_name":"pytest","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"tools/nmt_webapp/requirements.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:53.930Z","updated_at":"2025-02-07T01:42:53.930Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/tools/nmt_webapp/requirements.txt","dependencies":[{"id":21773639895,"package_name":"flask","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639896,"package_name":"flask_cors","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639897,"package_name":"nemo_toolkit","ecosystem":"pypi","requirements":"\u003e=1.0.0rc1","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"tools/speech_data_explorer/requirements.txt","sha":null,"kind":"manifest","created_at":"2025-02-07T01:42:54.000Z","updated_at":"2025-02-07T01:42:54.000Z","repository_link":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/speechllm-develop-yifanp/tools/speech_data_explorer/requirements.txt","dependencies":[{"id":21773639927,"package_name":"dash","ecosystem":"pypi","requirements":"\u003e=2.1.0","direct":true,"kind":"runtime","optional":false},{"id":21773639928,"package_name":"dash_bootstrap_components","ecosystem":"pypi","requirements":"\u003e=1.0.3","direct":true,"kind":"runtime","optional":false},{"id":21773639978,"package_name":"diff_match_patch","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639986,"package_name":"editdistance","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639987,"package_name":"jiwer","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639988,"package_name":"librosa","ecosystem":"pypi","requirements":"\u003e=0.9.1","direct":true,"kind":"runtime","optional":false},{"id":21773639989,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639990,"package_name":"plotly","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773639991,"package_name":"SoundFile","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21773640001,"package_name":"tqdm","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:50:49.289Z","updated_at":"2025-10-07T08:09:15.599Z","avatar_url":"https://github.com/pyf98.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/18084","html_url":"https://science.ecosyste.ms/projects/18084"}