OSS TanbouOverview
Whisper is a general-purpose speech recognition model trained on diverse audio. One Transformer model handles multilingual speech recognition, translation from non-English speech into English, and language identification through a CLI and Python API.
Based on official documentation; not hands-on tested · Content checked:
Transcribe audio with language identification and English translation
It represents several speech tasks as token-sequence prediction, supporting file transcription, spoken-language identification, and English translation with multilingual models. Sizes range from tiny through large plus the speed-oriented turbo model, with examples for both the CLI and Python.
Sources: [1]
For embedding multilingual audio processing in local workflows
It is a candidate for batch or Python application workflows that transcribe recordings and video, identify language, or translate non-English speech into English. Model size can be selected around accuracy, speed, and available VRAM.
Sources: [1]
Check memory, per-language accuracy, and translation support
README estimates range from roughly 1 to 10 GB of VRAM by model, and real speed and accuracy vary with language, speaking speed, and hardware. Turbo is not trained for translation, so English translation requires a multilingual tiny, base, small, medium, or large model. The runtime also needs Python, PyTorch-related packages, and ffmpeg.
Sources: [1]
Official sources
- [1]Whisper README(2026-09-13)
Supplemental curator note
Selected for using corporate and research authority plus several major ports and optimized implementations to expand discovery despite having no topics.
Growth trends
Last 30 days
108,957 Stars
Trend data is still being collected.
Built with
- Python
Categories and tags
Categories
GitHub dataView detailed GitHub data
- Stars
- 108,957
- Forks
- 13,205
- Watchers
- 783
- Open issues
- 0
- Contributors
- 83
- Primary language
- Python
- License
- MIT
- Repository last updated
- Aug 31, 2026
Explore next
- Ollama180,764 Stars
A runtime for downloading and running open models on a computer or server through a CLI and local API.
Go - Transformers165,220 Stars
A Python framework for inference and training with pretrained text, vision, audio, and multimodal models.
Python - AUTOMATIC1111 Stable Diffusion WebUI164,915 Stars
A Gradio UI for Stable Diffusion image generation, editing, model selection, extensions, and APIs.
Python - Dify155,555 Stars
A visual LLM application platform combining AI workflows, RAG, agents, model management, and observability.
TypeScript - LangChain146,205 Stars
A Python framework that connects models, tools, retrieval systems, and other components for LLM applications and agents.
Python
Report incorrect information
Tell us if any listing information is incorrect or outdated.