Convert spoken language into text using local Whisper transcription.
npx skills add https://github.com/jacardl/New-Radar --skill whisper-jacardl
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/jacardl/New-Radar/tree/main/backend/frameworks/hermes-agent/skills/mlops/models/whisper Command: npx skills add https://github.com/jacardl/New-Radar --skill whisper-jacardl
Whisper provides robust, multilingual speech recognition to convert audio to text and identify language, enabling automated transcription, captioning, and data labeling across languages.
Transcribe an audio file using whisper to obtain a text transcript in seconds.
High-intent search queries and answers about installing and using this skill.
Transcribe audio to text offline using local speech recognition models. This Skill loads Python packages like openai-whisper, transformers, and torch to perform speech-to-text conversion directly on your machine without requiring internet connectivity.
Yes, Whisper handles podcast transcription and video captioning by converting spoken language into text. It provides high-accuracy transcription across 99 languages, making it suitable for automated captioning workflows.
Whisper supports multilingual speech recognition and translation by identifying the spoken language and translating audio content to English. It enables automated transcription across 99 languages for multilingual analytics workflows.
Running local speech recognition requires loading models with Python packages such as openai-whisper, transformers, and torch. These dependencies enable offline speech-to-text and translation tasks without external API calls.
Offline transcription is suitable for meeting notes and multilingual analytics workflows. The Skill processes audio locally to generate text transcripts, enabling data labeling and language identification across various languages.
Running Whisper locally for speech-to-text requires sufficient computational resources to load models via torch and transformers. Processing large audio files offline may demand significant hardware capacity compared to cloud-based alternatives.
InverterNetworkTranscribe and translate multilingual audio into timestamped text and SRT subtitles.
trpc-groupTranscribe audio files into text or JSON using the Whisper model.
AshesOfTheUndeadTranscribe base64 encoded audio files into written text using the z-ai-web-dev-sdk.
surus-latBenchmark Whisper-family ASR models on FLEURS datasets with WER and CER metrics.
