{"id":46036795,"url":"https://github.com/thewh1teagle/gemma3-g2p","last_synced_at":"2026-03-01T05:31:31.369Z","repository":{"id":317137204,"uuid":"1066117744","full_name":"thewh1teagle/gemma3-g2p","owner":"thewh1teagle","description":"Transform Gemma3 to G2P task with unsloth","archived":false,"fork":false,"pushed_at":"2025-12-26T23:56:22.000Z","size":681,"stargazers_count":3,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-27T06:40:29.835Z","etag":null,"topics":["g2p","hebrew","linguistics","tts"],"latest_commit_sha":null,"homepage":"https://phonikud.github.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/thewh1teagle.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-29T03:41:36.000Z","updated_at":"2025-12-26T23:56:25.000Z","dependencies_parsed_at":"2025-09-29T05:44:32.784Z","dependency_job_id":null,"html_url":"https://github.com/thewh1teagle/gemma3-g2p","commit_stats":null,"previous_names":["thewh1teagle/gemma3-g2p"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/thewh1teagle/gemma3-g2p","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fgemma3-g2p","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fgemma3-g2p/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fgemma3-g2p/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fgemma3-g2p/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thewh1teagle","download_url":"https://codeload.github.com/thewh1teagle/gemma3-g2p/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thewh1teagle%2Fgemma3-g2p/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29960400,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-01T01:47:18.291Z","status":"online","status_checked_at":"2026-03-01T02:00:07.437Z","response_time":124,"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"}},"keywords":["g2p","hebrew","linguistics","tts"],"created_at":"2026-03-01T05:31:30.694Z","updated_at":"2026-03-01T05:31:31.342Z","avatar_url":"https://github.com/thewh1teagle.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Gemma3-G2P\n\nBased on https://unsloth.ai/blog/gemma3\n\n## Train\n\nSee `src/prepare_dataset.py` and `src/train.py`\n\n## Infer\n\nSee `src/infer.py`\n\n## Export to GGUF\n\nSee `src/export_gguf.py`\n\n## Inference with Ollama\n\nSee `ollama-infer/`\n\n## Inference with GGUF\n\nSee `gguf-infer/`\n\n## Continue fine-tuning\n\n```console\nmkdir outputs\nuv run hf download thewh1teagle/gemma3-270m-heb-g2p --local-dir ./outputs/checkpoint-10000\nuv run src/prepare_data.py --input_file raw_data.csv --output_file data.csv\nuv run src/train.py --report_to tensorboard --csv_file data.csv --resume_from_checkpoint --batch_size 16 --max_steps 90000000\n```\n\n## DGX Spark Setup\n\nTo fine-tune on DGX Spark, run these commands first:\n\n```console\nuv sync\nuv pip install -U torch torchvision --index-url https://download.pytorch.org/whl/cu130\nexport UV_SYNC=0\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthewh1teagle%2Fgemma3-g2p","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthewh1teagle%2Fgemma3-g2p","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthewh1teagle%2Fgemma3-g2p/lists"}