whisper
Whisper is OpenAI's multilingual speech recognition model for converting audio and video into text across 99 languages. It handles noisy recordings, supports translation to English, and offers multiple model sizes from lightweight to high-accuracy variants. Use it for podcasts, meeting transcription, video subtitles, and multilingual audio processing.
Whisper transcribes audio and video to text across 99 languages with high accuracy.
AI-generated summary based on this skill's SKILL.md
Install
NousResearch/hermes-agent/whisper · repository language: Python
git clone https://github.com/NousResearch/hermes-agent
cp -r hermes-agent/optional-skills/mlops/whisper ~/.claude/skills/whispernpx skillfed install NousResearch/hermes-agent/whisperFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What languages does Whisper support for speech to text transcription?
Whisper supports speech to text transcription across 99 languages, making it one of the most comprehensive multilingual speech recognition models available. This broad language coverage enables users to transcribe audio content from virtually any region and convert it to text accurately, regardless of the source language.
Can Whisper convert audio to text with high accuracy in noisy environments?
Yes, Whisper is specifically designed with noise robustness as a core feature. It converts speech to text with high accuracy even when processing noisy recordings, making it ideal for real-world scenarios like podcast transcription, meeting recordings, and other audio sources with background noise or imperfect recording conditions.
How do I set up the Whisper ASR model and what are the available variants?
Whisper offers multiple model sizes optimized for different use cases. The available variants range from lightweight models for faster processing to high-accuracy versions for demanding applications. Setup is straightforward, and you can choose the model size based on your accuracy requirements and computational resources. Whisper also includes a turbo model variant designed for improved speed.
Does Whisper automatically translate speech to English from other languages?
Yes, Whisper can translate foreign language audio to English automatically. Beyond transcription in the original language, it provides built-in translation capabilities, allowing you to convert multilingual speech directly into English text without requiring separate translation tools.
Can Whisper generate subtitles with timestamps from video files?
Whisper can generate subtitles or timestamps from media files, enabling you to create subtitle tracks in formats like SRT. This functionality makes it useful for video content creators who need to add captions with precise timing information to their videos or generate searchable transcripts.
Does Whisper support GPU acceleration for batch processing audio files?
Yes, Whisper supports GPU acceleration with CUDA for efficient batch processing of large audio files. This GPU support significantly speeds up transcription when processing multiple audio files, making it practical for handling large-scale transcription projects while maintaining accuracy across the entire batch.
SKILL.md
rendered from the published skill — quoted content, verbatim
Whisper - Robust Speech Recognition
OpenAI's multilingual speech recognition model.
When to use Whisper
Use when: - Speech-to-text transcription (99 languages) - Podcast/video transcription - Meeting notes automation - Translation to English - Noisy audio transcription - Multilingual audio processing
Metrics: - 72,900+ GitHub stars - 99 languages supported - Trained on 680,000 hours of audio - MIT License
Use alternatives instead: - AssemblyAI: Managed API, speaker diarization - Deepgram: Real-time streaming ASR - Google Speech-to-Text: Cloud-based
Quick start
Installation
# Requires Python 3.8-3.11
pip install -U openai-whisper
# Requires ffmpeg
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg
# Windows: choco install ffmpeg
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 2 files
optional-skills/mlops/whisper/SKILL.md
optional-skills/mlops/whisper/references/languages.md