Transcribe multilingual audio into text with optional English translation.
npx skills add https://github.com/quiznat/Hermes_Sapho --skill whisper-quiznat
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/quiznat/Hermes_Sapho/tree/main/.hermes/skills/mlops/models/whisper Command: npx skills add https://github.com/quiznat/Hermes_Sapho --skill whisper-quiznat
Whisper enables automatic transcription and understanding of spoken language across 99 languages, including translation to English and quick language identification, simplifying audio data workflows.
Install the whisper package and run a sample transcription on an audio file to see results.
High-intent search queries and answers about installing and using this skill.
Speech-to-text transcription processes audio files to generate searchable text across 99 languages. It identifies the spoken language automatically and transcribes podcasts, meetings, and lectures into readable text using the Whisper runtime.
Translation to English is supported alongside multilingual speech recognition. The Skill identifies the spoken source language and provides an English translation output, enabling cross-language content comprehension for audio data workflows.
Yes, Python is required along with Whisper runtime dependencies including openai-whisper, transformers, and torch. These packages provide the speech recognition processing logic and model execution environment required for audio transcription tasks.
Language identification detects the source language of an audio file automatically. By running audio through Whisper speech recognition, you can categorize and label audio files by their detected spoken language across 99 supported languages.
Yes, Whisper transcription supports multiple model sizes for CPU or GPU execution. You select the appropriate model size based on available hardware to optimize audio processing speed and speech-to-text generation performance.
icyzhTranscribe and translate audio files into text using OpenAI Whisper.
sdyckjq-labExtract plain text or timestamped captions from YouTube videos.
math-incTranscribe audio into text using Whisper multilingual speech recognition models.
WarrenZhu050413Generate and play multilingual text-to-speech audio with adjustable voices and speeds.
