Transcribe speech to text across 99 languages and translate to English.
npx skills add https://github.com/photonics-dhl/Hermes --skill whisper-photonics-dhl
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/photonics-dhl/Hermes/tree/main/hermes-home/skills/mlops/models/whisper Command: npx skills add https://github.com/photonics-dhl/Hermes --skill whisper-photonics-dhl
Transcribe speech to text across 99 languages and offer translations to English, enabling rapid transcription, captioning, and multilingual audio analysis.
Install the whisper package and run a transcription on your audio file to obtain a text transcript.
High-intent search queries and answers about installing and using this skill.
To transcribe multilingual audio to text, you can use this Skill to convert speech across 99 languages into written transcripts. It processes podcasts, meetings, and lectures automatically using openai-whisper and torch.
Yes, you can translate speech to English during audio transcription. This Skill provides on-demand translation to English for cross-language workflows, handling both multilingual transcription and English translation tasks.
Yes, you need Python dependencies including openai-whisper, transformers, and torch to run speech recognition. Optional GPU acceleration is supported to increase processing speed for large audio files.
The best way to generate captions for podcasts and meetings is using automatic multilingual speech recognition. This Skill transcribes spoken audio directly into text transcripts, supporting multiple model-size options for robust offline processing.
Yes, offline speech recognition works for multilingual video transcription. This Skill processes audio locally using model-size options, generating accurate text transcripts across 99 languages without requiring continuous internet access.
handsomelong922Transcribe and translate audio across 99 languages using Whisper.
koukoDownload YouTube subtitles and transcripts as SRT and TXT files using yt-dlp.
AlterLab-IEULoad, fine-tune, and deploy Hugging Face Transformer models across NLP, vision, and audio tasks.
VYRE-StudiosTranscribe speech from audio files into text using OpenAI Whisper models.
