Automatic Speech Recognition (ASR)
Transcribe audio segments to text using Whisper models. Use larger models (small, base, medium, large-v3) for better accuracy, or faster-whisper for optimized performance. Always align transcription timestamps with diarization segments for accurate speaker-labeled subtitles.
Install
npx skills add UCSB-NLP-Chang/Skill-Usage --skill Automatic Speech Recognition (ASR)git clone --depth 1 https://github.com/UCSB-NLP-Chang/Skill-Usage.git /tmp/Skill-Usage
mkdir -p ~/.claude/skills
cp -r /tmp/Skill-Usage/tasks/speaker-diarization-subtitles/environment/skills/automatic-speech-recognition ~/.claude/skills/Automatic-Speech-Recognition-ASR-Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Automatic Speech Recognition (ASR)
## Overview
After speaker diarization, you need to transcribe each speech segment to text. Whisper is the current state-of-the-art for ASR, with multiple model sizes offering different trade-offs between accuracy and speed.
## When to Use
- After speaker diarization is complete
- Need to generate speaker-labeled transcripts
- Creating subtitles from audio segments
- Converting speech segments to text
## Whisper Model Selection
### Model Size Comparison
| Model | Size | Speed | Accuracy | Best For |
|-------|------|-------|----------|----------|
| tiny | 39M | Fastest | Lowest | Quick testing, low accuracy needs |
| base | 74M | Fast | Low | Fast processing with moderate accuracy |
| small | 244M | Medium | Good | **Recommended balance** |
| medium | 769M | Slow | Very Good | High accuracy needs |
| large-v3 | 1550M | Slowest | **Best** | **Maximum accuracy** |
### Recommended: Use `small` or `large-v3`
**For best accuracy (recommended for this task):**
```python
import whisper
model = whisper.load_model("large-v3") # Best accuracy
result = model.transcribe(audio_path)
```
**For balanced performance:**
```python
import whisper
model = whisper.load_model("small") # Good balance
result = model.transcribe(audio_path)
```
## Faster-Whisper (Optimized Alternative)
For faster processing with similar accuracy, use `faster-whisper`:Details
- Skill name
Automatic Speech Recognition (ASR)- Repository
- UCSB-NLP-Chang/Skill-Usage
- Path
tasks/speaker-diarization-subtitles/environment/skills/automatic-speech-recognition/SKILL.md- Repo updated
- 8 April 2026
FAQ
What does the Automatic Speech Recognition (ASR) skill do?
Transcribe audio segments to text using Whisper models. Use larger models (small, base, medium, large-v3) for better accuracy, or faster-whisper for optimized performance. Always align transcription timestamps with diarization segments for accurate speaker-labeled subtitles.
How do I install the Automatic Speech Recognition (ASR) skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add UCSB-NLP-Chang/Skill-Usage --skill Automatic Speech Recognition (ASR). Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Automatic Speech Recognition (ASR) popular?
It lives in UCSB-NLP-Chang/Skill-Usage, which has 49 GitHub stars and 5 forks.
Related skills
Pubchem Database
49UCSB-NLP-Chang/Skill-Usage
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
Pymatgen
49UCSB-NLP-Chang/Skill-Usage
Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.
Rdkit
49UCSB-NLP-Chang/Skill-Usage
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.
Elevenlabs Tts
49UCSB-NLP-Chang/Skill-Usage
ElevenLabs Text-to-Speech API for high-quality speech synthesis.
Audiobook
49UCSB-NLP-Chang/Skill-Usage
Create audiobooks from web content or text files. Handles content fetching, text processing, and TTS conversion with automatic fallback between ElevenLabs, OpenAI TTS, and gTTS.
Energy Calculator
49UCSB-NLP-Chang/Skill-Usage
Calculate per-second RMS energy from audio files. Use when you need to analyze audio volume patterns, prepare data for silence/pause detection, or create an energy profile for audio analysis tasks.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.