# Requires Python 3.8-3.11
pip install -U openai-whisper

# Requires ffmpeg
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg
# Windows: choco install ffmpeg

import whisper

# Load model
model = whisper.load_model("base")

# Transcribe
result = model.transcribe("audio.mp3")

# Print text
print(result["text"])

# Access segments
for segment in result["segments"]:
    print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}")

# Available models
models = ["tiny", "base", "small", "medium", "large", "turbo"]

# Load specific model
model = whisper.load_model("turbo")  # Fastest, good quality

# Auto-detect language
result = model.transcribe("audio.mp3")

# Specify language (faster)
result = model.transcribe("audio.mp3", language="en")

# Supported: en, es, fr, de, it, pt, ru, ja, ko, zh, and 89 more

# Transcription (default)
result = model.transcribe("audio.mp3", task="transcribe")

# Translation to English
result = model.transcribe("spanish.mp3", task="translate")
# Input: Spanish audio → Output: English text

# Improve accuracy with context
result = model.transcribe(
    "audio.mp3",
    initial_prompt="This is a technical podcast about machine learning and AI."
)

# Helps with:
# - Technical terms
# - Proper nouns
# - Domain-specific vocabulary

# Word-level timestamps
result = model.transcribe("audio.mp3", word_timestamps=True)

for segment in result["segments"]:
    for word in segment["words"]:
        print(f"{word['word']} ({word['start']:.2f}s - {word['end']:.2f}s)")

# Retry with different temperatures if confidence low
result = model.transcribe(
    "audio.mp3",
    temperature=(0.0, 0.2, 0.4, 0.6, 0.8, 1.0)
)

# Basic transcription
whisper audio.mp3

# Specify model
whisper audio.mp3 --model turbo

# Output formats
whisper audio.mp3 --output_format txt     # Plain text
whisper audio.mp3 --output_format srt     # Subtitles
whisper audio.mp3 --output_format vtt     # WebVTT
whisper audio.mp3 --output_format json    # JSON with timestamps

# Language
whisper audio.mp3 --language Spanish

# Translation
whisper spanish.mp3 --task translate

import os

audio_files = ["file1.mp3", "file2.mp3", "file3.mp3"]

for audio_file in audio_files:
    print(f"Transcribing {audio_file}...")
    result = model.transcribe(audio_file)

    # Save to file
    output_file = audio_file.replace(".mp3", ".txt")
    with open(output_file, "w") as f:
        f.write(result["text"])

# For streaming audio, use faster-whisper
# pip install faster-whisper

from faster_whisper import WhisperModel

model = WhisperModel("base", device="cuda", compute_type="float16")

# Transcribe with streaming
segments, info = model.transcribe("audio.mp3", beam_size=5)

for segment in segments:
    print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")

import whisper

# Automatically uses GPU if available
model = whisper.load_model("turbo")

# Force CPU
model = whisper.load_model("turbo", device="cpu")

# Force GPU
model = whisper.load_model("turbo", device="cuda")

# 10-20× faster on GPU

# Generate SRT subtitles
whisper video.mp4 --output_format srt --language English

# Output: video.srt

from langchain.document_loaders import WhisperTranscriptionLoader

loader = WhisperTranscriptionLoader(file_path="audio.mp3")
docs = loader.load()

# Use transcription in RAG
from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings

vectorstore = Chroma.from_documents(docs, OpenAIEmbeddings())

# Use ffmpeg to extract audio
ffmpeg -i video.mp4 -vn -acodec pcm_s16le audio.wav

# Then transcribe
whisper audio.wav