TacoSkill LAB
TacoSkill LAB
HomeSkillHubCreatePlaygroundSkillKit
© 2026 TacoSkill LAB
AboutPrivacyTerms
  1. Home
  2. /
  3. SkillHub
  4. /
  5. whisper
Improve

whisper

7.0

by zechenzhangAGI

110Favorites
268Upvotes
0Downvotes

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

speech-to-text

7.0

Rating

0

Installs

AI & LLM

Category

Quick Review

Excellent skill with comprehensive coverage of Whisper's capabilities. The description clearly explains when to use it, and SKILL.md provides detailed code examples, model selection guidance, and practical usage patterns. Strong task knowledge with working code for transcription, translation, batch processing, and CLI usage. Well-structured with logical sections and a clear progression from basics to advanced topics. Novelty is moderate-to-good: while Whisper is accessible via simple pip install and CLI, this skill consolidates best practices, model selection logic, GPU optimization, and integration patterns that would require significant token usage for a CLI agent to discover independently. The references/languages.md file is appropriately separated. Minor improvement could include more explicit decision trees for model selection based on constraints.

LLM Signals

Description coverage9
Task knowledge9
Structure8
Novelty7

GitHub Signals

891
74
19
2
Last commit 0 days ago

Publisher

zechenzhangAGI

zechenzhangAGI

Skill Author

Related Skills

rag-architectprompt-engineerfine-tuning-expert

Loading SKILL.md…

Try onlineView on GitHub

Publisher

zechenzhangAGI avatar
zechenzhangAGI

Skill Author

Related Skills

rag-architect

Jeffallan

7.0

prompt-engineer

Jeffallan

7.0

fine-tuning-expert

Jeffallan

6.4

mcp-developer

Jeffallan

6.4
Try online