Audio Transcribe

1. Environment Setup

AUTO_YES=1 bash $SCRIPTS/setup_env.sh
Or force CPU:  AUTO_YES=1 bash $SCRIPTS/setup_env.sh cpu

The setup script patches FunASR's spectral clustering for O(N²·k) performance. Without this, recordings over ~1 hour hang for hours during speaker clustering.

2. Run Transcription

Output files are written to the current working directory.

LLM cleanup (Phase 3) is opt-in. By default, transcription runs locally without contacting any external service. To enable LLM-powered ASR correction and speaker name refinement, pass --model . Use LLM cleanup when:

> ⚠️ Data Privacy: When LLM cleanup is enabled via --model, transcript > excerpts are sent to external LLM providers (AWS Bedrock, Anthropic, or > OpenAI depending on the model ID). Use --skip-llm or omit --model to > keep all data local. For Bedrock, boto3 uses the standard AWS credential > chain (IAM role, SSO, ~/.aws/credentials, env vars).

# Chinese meeting with hotwords (local-only, no LLM)
python3 $SCRIPTS/transcribe.py meeting.wav \
    --lang zh --num-speakers 9 --hotwords hotwords.txt
English meeting with speaker names
python3 $SCRIPTS/transcribe.py meeting.wav \
    --lang en --speakers "Alice,Bob,Carol,Dave"
Auto-detect language (zh/en/ja/ko/yue)
python3 $SCRIPTS/transcribe.py meeting.wav \
    --lang auto --num-speakers 6
Whisper for any language
python3 $SCRIPTS/transcribe.py meeting.wav \
    --lang whisper --num-speakers 4
Enable LLM cleanup for polished output (requires --model)
Bedrock (uses AWS credential chain: IAM role, SSO, ~/.aws/credentials)
python3 $SCRIPTS/transcribe.py meeting.wav \
    --lang zh --num-speakers 9 --hotwords hotwords.txt \
    --provider bedrock --model us.anthropic.claude-sonnet-4-6
Bedrock "global" cross-region profile (recent AWS deployments)
python3 $SCRIPTS/transcribe.py meeting.wav \
    --provider bedrock --model global.anthropic.claude-sonnet-4-6
Bedrock via litellm-style wrapper (supported; prefix is stripped for boto3)
python3 $SCRIPTS/transcribe.py meeting.wav \
    --provider bedrock --model amazon-bedrock/global.anthropic.claude-sonnet-4-6
Anthropic API (requires ANTHROPIC_API_KEY env var)
python3 $SCRIPTS/transcribe.py meeting.wav \
    --provider anthropic --model claude-sonnet-4-6
OpenAI-compatible API (requires OPENAI_API_KEY env var)
python3 $SCRIPTS/transcribe.py meeting.wav \
    --provider openai --model gpt-4o
Full pipeline with all supporting files + LLM (best quality)
python3 $SCRIPTS/transcribe.py episode.m4a \
    --lang zh --num-speakers 2 \
    --hotwords hotwords.txt \
    --speakers "关羽,张飞" \
    --speaker-context speaker-context.json \
    --reference show-notes.md \
    --model us.anthropic.claude-sonnet-4-6
Resume interrupted LLM cleanup
python3 $SCRIPTS/transcribe.py meeting.wav \
    --skip-transcribe --model us.anthropic.claude-sonnet-4-6

3. Verify Speaker Labels

If the transcript has swapped speaker labels (common with podcasts), the verification script can detect and fix mismatches using LLM analysis:

# Dry-run: check if host/guest are swapped
python3 $SCRIPTS/verify_speakers.py podcast_raw_transcript.json \
    --speakers "关羽,张飞" \
    --speaker-context speaker-context.json
Apply the fix
python3 $SCRIPTS/verify_speakers.py podcast_raw_transcript.json \
    --speakers "关羽,张飞" \
    --speaker-context speaker-context.json --fix
Multi-speaker meeting: full reassignment
python3 $SCRIPTS/verify_speakers.py meeting_raw_transcript.json \
    --speakers "Alice,Bob,Carol,Dave" \
    --speaker-context speaker-context.json --fix
Then regenerate the markdown with corrected labels
python3 $SCRIPTS/transcribe.py original.m4a \
    --skip-transcribe --clean-cache

The script analyzes the first 5 minutes (configurable with --minutes) and auto-detects podcast (2 speakers, swap detection) vs meeting (N speakers, full reassignment).