{"id":28384436,"url":"https://github.com/runpod-workers/worker-faster_whisper","last_synced_at":"2026-03-07T03:03:29.267Z","repository":{"id":171056324,"uuid":"647368089","full_name":"runpod-workers/worker-faster_whisper","owner":"runpod-workers","description":"faster-whisper as serverless endpoint","archived":false,"fork":false,"pushed_at":"2025-11-21T06:33:09.000Z","size":2073,"stargazers_count":125,"open_issues_count":18,"forks_count":109,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-11-21T08:30:20.344Z","etag":null,"topics":["ai","docker","faster-whsiper","runpod","whisper"],"latest_commit_sha":null,"homepage":"https://runpod.io","language":"Python","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/runpod-workers.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-05-30T16:17:36.000Z","updated_at":"2025-11-11T04:36:07.000Z","dependencies_parsed_at":"2023-09-23T18:44:52.953Z","dependency_job_id":"29d956c8-d33e-43b1-bae6-25b1246b1e9a","html_url":"https://github.com/runpod-workers/worker-faster_whisper","commit_stats":null,"previous_names":["runpod-workers/worker-faster_whisper"],"tags_count":17,"template":false,"template_full_name":null,"purl":"pkg:github/runpod-workers/worker-faster_whisper","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runpod-workers%2Fworker-faster_whisper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runpod-workers%2Fworker-faster_whisper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runpod-workers%2Fworker-faster_whisper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runpod-workers%2Fworker-faster_whisper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/runpod-workers","download_url":"https://codeload.github.com/runpod-workers/worker-faster_whisper/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runpod-workers%2Fworker-faster_whisper/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30206339,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-06T19:07:06.838Z","status":"online","status_checked_at":"2026-03-07T02:00:06.765Z","response_time":53,"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":["ai","docker","faster-whsiper","runpod","whisper"],"created_at":"2025-05-30T08:38:38.891Z","updated_at":"2026-03-07T03:03:29.248Z","avatar_url":"https://github.com/runpod-workers.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Faster Whisper Logo](https://5ccaof7hvfzuzf4p.public.blob.vercel-storage.com/banner-pjbGKw0buxbWGhMVC165Gf9qgqWo7I.jpeg)\n\n[Faster Whisper](https://github.com/guillaumekln/faster-whisper) is designed to process audio files using various Whisper models, with options for transcription formatting, language translation and more.\n\n---\n\n[![RunPod](https://api.runpod.io/badge/runpod-workers/worker-faster_whisper)](https://www.runpod.io/console/hub/runpod-workers/worker-faster_whisper)\n\n---\n\n## Models\n\n- tiny\n- base\n- small\n- medium\n- large-v1\n- large-v2\n- large-v3\n- distil-large-v2\n- distil-large-v3\n- turbo\n\n## Input\n\n| Input                               | Type  | Description                                                                                                                                                            |\n| ----------------------------------- | ----- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `audio`                             | Path  | URL to Audio file                                                                                                                                                      |\n| `audio_base64`                      | str   | Base64-encoded audio file                                                                                                                                              |\n| `model`                             | str   | Choose a Whisper model. Choices: \"tiny\", \"base\", \"small\", \"medium\", \"large-v1\", \"large-v2\", \"large-v3\", \"distil-large-v2\", \"distil-large-v3\", \"turbo\". Default: \"base\" |\n| `transcription`                     | str   | Choose the format for the transcription. Choices: \"plain_text\", \"formatted_text\", \"srt\", \"vtt\". Default: \"plain_text\"                                                  |\n| `translate`                         | bool  | Translate the text to English when set to True. Default: False                                                                                                         |\n| `translation`                       | str   | Choose the format for the translation. Choices: \"plain_text\", \"formatted_text\", \"srt\", \"vtt\". Default: \"plain_text\"                                                    |\n| `language`                          | str   | Language spoken in the audio, specify None to perform language detection. Default: None                                                                                |\n| `temperature`                       | float | Temperature to use for sampling. Default: 0                                                                                                                            |\n| `best_of`                           | int   | Number of candidates when sampling with non-zero temperature. Default: 5                                                                                               |\n| `beam_size`                         | int   | Number of beams in beam search, only applicable when temperature is zero. Default: 5                                                                                   |\n| `patience`                          | float | Optional patience value to use in beam decoding. Default: None                                                                                                         |\n| `length_penalty`                    | float | Optional token length penalty coefficient (alpha). Default: None                                                                                                       |\n| `suppress_tokens`                   | str   | Comma-separated list of token ids to suppress during sampling. Default: \"-1\"                                                                                           |\n| `initial_prompt`                    | str   | Optional text to provide as a prompt for the first window. Default: None                                                                                               |\n| `condition_on_previous_text`        | bool  | If True, provide the previous output of the model as a prompt for the next window. Default: True                                                                       |\n| `temperature_increment_on_fallback` | float | Temperature to increase when falling back when the decoding fails. Default: 0.2                                                                                        |\n| `compression_ratio_threshold`       | float | If the gzip compression ratio is higher than this value, treat the decoding as failed. Default: 2.4                                                                    |\n| `logprob_threshold`                 | float | If the average log probability is lower than this value, treat the decoding as failed. Default: -1.0                                                                   |\n| `no_speech_threshold`               | float | If the probability of the token is higher than this value, consider the segment as silence. Default: 0.6                                                               |\n| `enable_vad`                        | bool  | If True, use the voice activity detection (VAD) to filter out parts of the audio without speech. This step is using the Silero VAD model. Default: False               |\n| `word_timestamps`                   | bool  | If True, include word timestamps in the output. Default: False                                                                                                         |\n\n### Example\n\nThe following inputs can be used for testing the model:\n\n```json\n{\n  \"input\": {\n    \"audio\": \"https://github.com/runpod-workers/sample-inputs/raw/main/audio/gettysburg.wav\",\n    \"model\": \"turbo\"\n  }\n}\n```\n\nproducing an output like this:\n\n```json\n{\n  \"segments\": [\n    {\n      \"id\": 1,\n      \"seek\": 106,\n      \"start\": 0.11,\n      \"end\": 3.11,\n      \"text\": \" Hello and welcome!\",\n      \"tokens\": [50364, 25, 7, 287, 50514],\n      \"temperature\": 0.1,\n      \"avg_logprob\": -0.8348079785480325,\n      \"compression_ratio\": 0.5789473684210527,\n      \"no_speech_prob\": 0.1453857421875\n    }\n  ],\n  \"detected_language\": \"en\",\n  \"transcription\": \"Hello and welcome!\",\n  \"translation\": null,\n  \"device\": \"cuda\",\n  \"model\": \"turbo\",\n  \"translation_time\": 0.3796223163604736\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frunpod-workers%2Fworker-faster_whisper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frunpod-workers%2Fworker-faster_whisper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frunpod-workers%2Fworker-faster_whisper/lists"}