OpenAI Whisper

# openai-whisper (latest, v20250625+) · Python >=3.9
# 1) ffmpeg is a hard runtime dep — install it first.
#    macOS:    brew install ffmpeg
#    Ubuntu:   sudo apt update && sudo apt install ffmpeg
#    Windows:  choco install ffmpeg     (or scoop install ffmpeg)

pip install -U openai-whisper

# 2) Transcribe a file directly to SRT subtitles.
whisper input.mp3 --model turbo --output_format srt

# Other useful flags:
#   --language Japanese        force a language (skip auto-detect)
#   --task translate           translate to English (not supported by 'turbo')
#   --device cuda              run on GPU
#   --output_format all        write txt + srt + vtt + tsv + json

# Python >=3.9, openai-whisper installed.
import whisper

model = whisper.load_model("turbo")   # or tiny / base / small / medium / large-v3

result = model.transcribe(
    "input.mp3",
    word_timestamps=True,
    # language="en",                 # skip auto-detect if you know it
    # task="translate",              # translate to English (not on 'turbo')
)

print(result["text"])
for seg in result["segments"]:
    print(f"[{seg['start']:6.2f} -> {seg['end']:6.2f}] {seg['text']}")
    for w in seg.get("words", []):
        print(f"   {w['start']:6.2f}-{w['end']:6.2f}  {w['word']!r}")

# CUDA toolkit + a matching torch build already installed.
import whisper

model = whisper.load_model("large-v3", device="cuda")

result = model.transcribe(
    "podcast.wav",
    fp16=True,                 # default True on CUDA; explicit here for clarity
    beam_size=5,
    best_of=5,
    temperature=0.0,
    # condition_on_previous_text=False,  # try if you see hallucination loops
)

print(result["text"][:500])