Spaces:
Runtime error
Runtime error
| # Schema version for tracking updates to the schema format | |
| schema-version: "v0.5.0" | |
| # Component Information | |
| component-name: odtp-pyannote-whisper | |
| component-version: "v0.1.1" | |
| component-license: Apache 2.0 | |
| component-type: ephemeral | |
| component-description: Transcribe or translate audio files using Whisper and Pyannote for speaker diarization | |
| component-authors: | |
| - name: Carlos Vivar Rios | |
| orcid: null | |
| component-repository: | |
| url: "https://github.com/odtp-org/odtp-pyannote-whisper" | |
| doi: null | |
| component-docker-image: null | |
| tags: | |
| - audio | |
| - transcription | |
| - translation | |
| - whisper | |
| - pyannote | |
| # Tool Information | |
| tools: | |
| - tool-name: whisper | |
| tool-authors: | |
| - name: OpenAI | |
| orcid: null | |
| tool-version: latest | |
| tool-repository: | |
| url: "https://github.com/openai/whisper" | |
| doi: null | |
| tool-license: MIT | |
| - tool-name: pyannote | |
| tool-authors: | |
| - name: Hervé Bredin | |
| orcid: null | |
| tool-version: latest | |
| tool-repository: | |
| url: "https://github.com/pyannote/pyannote-audio" | |
| doi: null | |
| tool-license: MIT | |
| # Secrets (ENV variables) | |
| secrets: | |
| - name: HF_TOKEN | |
| description: Hugging Face API token for accessing pyannote models | |
| type: str | |
| # Build Arguments (if any) | |
| build-args: null | |
| # Exposed Ports | |
| ports: null | |
| # Parameters for the Component | |
| parameters: | |
| - name: MODEL | |
| default-value: large-v3 | |
| datatype: str | |
| description: Whisper model to use for transcription/translation | |
| parameter-bounds: null | |
| options: | |
| - tiny | |
| - base | |
| - small | |
| - medium | |
| - large | |
| - large-v2 | |
| - large-v3 | |
| allow-custom-value: false | |
| - name: TASK | |
| default-value: transcribe | |
| datatype: str | |
| description: Task to perform (transcribe or translate) | |
| parameter-bounds: null | |
| options: | |
| - transcribe | |
| - translate | |
| allow-custom-value: false | |
| - name: LANGUAGE | |
| default-value: auto | |
| datatype: str | |
| description: Source language code (use 'auto' for auto-detection) | |
| parameter-bounds: null | |
| options: | |
| - auto | |
| - en | |
| - es | |
| - fr | |
| - de | |
| - it | |
| - pt | |
| - nl | |
| - ja | |
| - zh | |
| - ru | |
| allow-custom-value: true | |
| # Data Inputs | |
| data-inputs: | |
| - name: INPUT_FILE | |
| type: .wav | |
| path: /odtp/odtp-input | |
| description: Input audio file in WAV format | |
| naming-convention: null | |
| # Data Outputs | |
| data-outputs: | |
| - name: OUTPUT_FILE | |
| type: .srt | |
| path: /odtp/odtp-output | |
| description: Transcription/translation output in SRT format with speaker diarization | |
| naming-convention: null | |
| - name: OUTPUT_JSON_FILE | |
| type: .json | |
| path: /odtp/odtp-output | |
| description: Transcription/translation output in JSON format with speaker diarization | |
| naming-convention: null | |
| - name: OUTPUT_AUDIO_FILE | |
| type: .wav | |
| path: /odtp/odtp-output | |
| description: Audio in wav format | |
| naming-convention: null | |
| - name: OUTPUT_PARAGRAPHS_FILE | |
| type: .json | |
| path: /odtp/odtp-output | |
| description: Markdown file with the paragraphs containing speaker diarization and transcription/translation | |
| naming-convention: null | |
| - name: OUTPUT_MD_FILE | |
| type: .md | |
| path: /odtp/odtp-output | |
| description: Markdown file with the speaker diarization and transcription/translation | |
| naming-convention: null | |
| - name: OUTPUT_PDF_FILE | |
| type: .pdf | |
| path: /odtp/odtp-output | |
| description: PDF file with the speaker diarization and transcription/translation | |
| naming-convention: null | |
| # Validation Schemas (Future Development) | |
| schema-input: null | |
| schema-output: null | |
| # Device Requirements | |
| devices: | |
| - type: gpu | |
| required: true |