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.

49 stars 5 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add UCSB-NLP-Chang/Skill-Usage --skill Automatic Speech Recognition (ASR)
Manual install
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`:
Read the full skill on GitHub

Details

Skill name
Automatic Speech Recognition (ASR)
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

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.