admin-valentin/WhisperLiveKit
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

solve #100

Browse source
This commit is contained in:
Quentin Fuxa 2025-03-24 20:38:47 +01:00
parent ccf99cecdf
commit e9022894b2
4 changed files with 18 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -72,6 +72,12 @@ pip install tokenize_uk # If you work with Ukrainian text
# If you want to use diarization # If you want to use diarization
pip install diart pip install diart
# Optional backends. Default is faster-whisper
pip install whisperlivekit[whisper] # Original Whisper backend
pip install whisperlivekit[whisper-timestamped] # Whisper with improved timestamps
pip install whisperlivekit[mlx-whisper] # Optimized for Apple Silicon
pip install whisperlivekit[openai] # OpenAI API backend
``` ```
### Get access to 🎹 pyannote models ### Get access to 🎹 pyannote models

7
setup.py
View file

@ -1,8 +1,7 @@
from setuptools import setup, find_packages from setuptools import setup, find_packages
setup( setup(
name="whisperlivekit", name="whisperlivekit",
version="0.1.2", version="0.1.3",
description="Real-time, Fully Local Whisper's Speech-to-Text and Speaker Diarization", description="Real-time, Fully Local Whisper's Speech-to-Text and Speaker Diarization",
long_description=open("README.md", "r", encoding="utf-8").read(), long_description=open("README.md", "r", encoding="utf-8").read(),
long_description_content_type="text/markdown", long_description_content_type="text/markdown",
@ -22,6 +21,10 @@ setup(
"diarization": ["diart"], "diarization": ["diart"],
"vac": ["torch"], "vac": ["torch"],
"sentence": ["mosestokenizer", "wtpsplit"], "sentence": ["mosestokenizer", "wtpsplit"],
"whisper": ["whisper"],
"whisper-timestamped": ["whisper-timestamped"],
"mlx-whisper": ["mlx-whisper"],
"openai": ["openai"],
}, },
package_data={ package_data={
'whisperlivekit': ['web/*.html'], 'whisperlivekit': ['web/*.html'],

4
whisperlivekit/core.py
View file

@ -1,7 +1,7 @@
try: try:
from whisperlivekit.whisper_streaming_custom.whisper_online import backend_factory, warmup_asr from whisperlivekit.whisper_streaming_custom.whisper_online import backend_factory, warmup_asr
except: except ImportError:
from whisper_streaming_custom.whisper_online import backend_factory, warmup_asr from .whisper_streaming_custom.whisper_online import backend_factory, warmup_asr
from argparse import Namespace, ArgumentParser from argparse import Namespace, ArgumentParser
def parse_args(): def parse_args():

7
whisperlivekit/whisper_streaming_custom/backends.py
View file

@ -3,7 +3,10 @@ import logging
import io import io
import soundfile as sf import soundfile as sf
import math import math
import torch try:
import torch
except ImportError:
torch = None
from typing import List from typing import List
import numpy as np import numpy as np
from whisperlivekit.timed_objects import ASRToken from whisperlivekit.timed_objects import ASRToken
@ -102,7 +105,7 @@ class FasterWhisperASR(ASRBase):
model_size_or_path = modelsize model_size_or_path = modelsize
else: else:
raise ValueError("Either modelsize or model_dir must be set") raise ValueError("Either modelsize or model_dir must be set")
device = "cuda" if torch.cuda.is_available() else "cpu" device = "cuda" if torch and torch.cuda.is_available() else "cpu"
compute_type = "float16" if device == "cuda" else "float32" compute_type = "float16" if device == "cuda" else "float32"
model = WhisperModel( model = WhisperModel(