whisperX

# whisperx 3.8.x · Python >=3.9 · CUDA 12 for GPU
pip install whisperx

# transcribe a file, write subtitles
whisperx input.mp3 \
  --model large-v3 \
  --compute_type float16 \
  --batch_size 16 \
  --output_format srt

# CPU-only laptop fallback
whisperx input.mp3 \
  --model medium \
  --device cpu \
  --compute_type int8 \
  --batch_size 4

# 1. Sign in at https://hf.co and accept the user conditions on:
#      https://huggingface.co/pyannote/segmentation-3.0
#      https://huggingface.co/pyannote/speaker-diarization-3.1
# 2. Create a read token at https://hf.co/settings/tokens
# 3. Export it (never hardcode):
export HF_TOKEN="hf_...your_token_here..."

# 4. Transcribe + align + diarize in one pass
whisperx input.mp3 \
  --model large-v3 \
  --diarize \
  --hf_token "${HF_TOKEN}" \
  --min_speakers 2 \
  --max_speakers 4 \
  --output_format srt

# karaoke-style word highlighting in the SRT
whisperx input.mp3 --model large-v3 --diarize \
  --hf_token "${HF_TOKEN}" --highlight_words True --output_format srt

import os
import whisperx
from whisperx.diarize import DiarizationPipeline

device = "cuda"
batch_size = 16
compute_type = "float16"   # "int8" on low-VRAM GPUs
audio_file = "input.mp3"
HF_TOKEN = os.environ["HF_TOKEN"]   # never hardcode

# 1. Transcribe (faster-whisper under the hood)
model = whisperx.load_model("large-v3", device, compute_type=compute_type)
audio = whisperx.load_audio(audio_file)
result = model.transcribe(audio, batch_size=batch_size)

# 2. Forced alignment (wav2vec2)
model_a, metadata = whisperx.load_align_model(
    language_code=result["language"], device=device,
)
result = whisperx.align(
    result["segments"], model_a, metadata, audio, device,
    return_char_alignments=False,
)

# 3. Diarize + assign speakers to each word
diarize_model = DiarizationPipeline(use_auth_token=HF_TOKEN, device=device)
diarize_segments = diarize_model(audio, min_speakers=2, max_speakers=4)
result = whisperx.assign_word_speakers(diarize_segments, result)

for seg in result["segments"]:
    speaker = seg.get("speaker", "?")
    print(f"[{seg['start']:6.2f} -> {seg['end']:6.2f}] {speaker}: {seg['text']}")