mirror of
https://github.com/xtekky/gpt4free.git
synced 2025-12-06 02:30:41 -08:00
9461949542
- Added UUID-based "x-xai-request-id" header and 403 error handling in Grok.py - Updated backend_api.py to handle empty media results and unsupported file types with error raising and file cleanup - Simplified render logic in website.py by removing is_live flag and related code - Changed "audio/wav" MIME type to "audio/x-wav" in image/__init__.py - Added is_valid_media and is_valid_audio functions to image/__init__.py for stricter media validation - Enhanced MarkItDown integration in markitdown/__init__.py with convert_stream method supporting non-seekable streams - Modified _transcribe_audio.py to use recognize_faster_whisper if available, fallback to recognize_google - Updated providers/helper.py to prioritize "text" key in to_string function - Improved stream_read_files in files.py to skip DOWNLOADS_FILE and adjust code block formatting - Added get_filename_from_url utility in files.py for consistent filename generation from URLs - Enhanced download_urls in files.py to use MarkItDown for URL conversion and improved error logging - Improved render_part and related functions in media.py to use new media validation logic and handle more cases - Adjusted merge_media and render_messages in media.py for stricter part filtering and validation
54 lines
2.1 KiB
Python
54 lines
2.1 KiB
Python
import io
|
|
import sys
|
|
from typing import BinaryIO
|
|
from markitdown._exceptions import MissingDependencyException
|
|
|
|
# Try loading optional (but in this case, required) dependencies
|
|
# Save reporting of any exceptions for later
|
|
_dependency_exc_info = None
|
|
try:
|
|
# Suppress some warnings on library import
|
|
import warnings
|
|
|
|
with warnings.catch_warnings():
|
|
warnings.filterwarnings("ignore", category=DeprecationWarning)
|
|
warnings.filterwarnings("ignore", category=SyntaxWarning)
|
|
import speech_recognition as sr
|
|
import pydub
|
|
except ImportError:
|
|
# Preserve the error and stack trace for later
|
|
_dependency_exc_info = sys.exc_info()
|
|
|
|
|
|
def transcribe_audio(file_stream: BinaryIO, *, audio_format: str = "wav", language: str = None) -> str:
|
|
# Check for installed dependencies
|
|
if _dependency_exc_info is not None:
|
|
raise MissingDependencyException(
|
|
"Speech transcription requires installing MarkItdown with the [audio-transcription] optional dependencies. E.g., `pip install markitdown[audio-transcription]` or `pip install markitdown[all]`"
|
|
) from _dependency_exc_info[
|
|
1
|
|
].with_traceback( # type: ignore[union-attr]
|
|
_dependency_exc_info[2]
|
|
)
|
|
|
|
if audio_format in ["wav", "aiff", "flac"]:
|
|
audio_source = file_stream
|
|
elif audio_format in ["mp3", "mp4", "webm"]:
|
|
audio_segment = pydub.AudioSegment.from_file(file_stream, format=audio_format)
|
|
|
|
audio_source = io.BytesIO()
|
|
audio_segment.export(audio_source, format="wav")
|
|
audio_source.seek(0)
|
|
else:
|
|
raise ValueError(f"Unsupported audio format: {audio_format}")
|
|
|
|
recognizer = sr.Recognizer()
|
|
with sr.AudioFile(audio_source) as source:
|
|
audio = recognizer.record(source)
|
|
if language is None:
|
|
language = "en-US"
|
|
try:
|
|
transcript = recognizer.recognize_faster_whisper(audio, language=language.split("-")[0]).strip()
|
|
except ImportError:
|
|
transcript = recognizer.recognize_google(audio, language=language).strip()
|
|
return "[No speech detected]" if transcript == "" else transcript.strip()
|