recognize_faster_whisper()

recognize_faster_whisper(
    audio_data: AudioData,
    model: str = "base",
    show_dict: bool = False,
    init_options: dict | None = None,
    language: str | None = None,
    task: Literal["transcribe", "translate"] = "transcribe",
    beam_size: int = 5,
    **transcribe_options
) -> str | dict

pip install SpeechRecognition[faster-whisper]

pip install faster-whisper

import speech_recognition as sr

r = sr.Recognizer()

# From microphone
with sr.Microphone() as source:
    print("Say something!")
    audio = r.listen(source)

try:
    text = r.recognize_faster_whisper(audio, model="base")
    print(f"You said: {text}")
except sr.UnknownValueError:
    print("Could not understand audio")
except sr.RequestError as e:
    print(f"Error: {e}")

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    audio = r.listen(source)

# Specify language for faster processing
text = r.recognize_faster_whisper(
    audio,
    model="small",
    language="en"
)
print(f"English transcription: {text}")

import speech_recognition as sr

r = sr.Recognizer()

with sr.AudioFile('audio.wav') as source:
    audio = r.record(source)

text = r.recognize_faster_whisper(audio, model="medium")
print(f"Transcription: {text}")

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    audio = r.listen(source)

# Get detailed response with segments and timestamps
result = r.recognize_faster_whisper(
    audio,
    model="base",
    show_dict=True
)

print(f"Text: {result['text']}")
print(f"Language: {result['language']}")
print(f"Segments: {len(result['segments'])}")

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

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    print("Say something in any language...")
    audio = r.listen(source)

# Transcribe and translate to English
text = r.recognize_faster_whisper(
    audio,
    model="base",
    task="translate"
)
print(f"English translation: {text}")

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    audio = r.listen(source)

# Use GPU with float16 precision for faster processing
text = r.recognize_faster_whisper(
    audio,
    model="large-v3",
    init_options={
        "device": "cuda",
        "compute_type": "float16"
    }
)
print(f"GPU-accelerated: {text}")

import speech_recognition as sr

r = sr.Recognizer()

with sr.Microphone() as source:
    audio = r.listen(source)

# Specify custom download location
text = r.recognize_faster_whisper(
    audio,
    model="base",
    init_options={
        "download_root": "/path/to/models"
    }
)