| 知乎专栏 |
https://github.com/openai/whisper
import openai
audio_file= open("/path/to/file/audio.mp3", "rb")
transcript = openai.Audio.transcribe("whisper-1", audio_file)
pip install --upgrade pip
pip install -U funasr modelscope
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "iic/SenseVoiceSmall"
model = AutoModel(
model=model_dir,
# trust_remote_code=True,
# remote_code="./model.py",
vad_model="fsmn-vad",
vad_kwargs={"max_single_segment_time": 30000},
# device="cuda:0",
disable_update=True
)
# en
res = model.generate(
input=f"{model.model_path}/example/zh.mp3",
cache={},
language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
use_itn=True,
batch_size_s=60,
merge_vad=True, #
merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)
/Users/neo/tmp/social/.venv/bin/python /Users/neo/tmp/social/test.py
funasr version: 1.3.0.
Downloading Model from https://www.modelscope.cn to directory: /Users/neo/.cache/modelscope/hub/models/iic/SenseVoiceSmall
WARNING:root:trust_remote_code: False
Downloading Model from https://www.modelscope.cn to directory: /Users/neo/.cache/modelscope/hub/models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch
WARNING:root:trust_remote_code: False
rtf_avg: 0.009: 100%|██████████| 1/1 [00:00<00:00, 19.43it/s]
0%| | 0/1 [00:00<?, ?it/s]
0%| | 0/1 [00:00<?, ?it/s]
100%|██████████| 1/1 [00:00<00:00, 1.86it/s]
{'load_data': '0.000', 'extract_feat': '0.003', 'forward': '0.538', 'batch_size': '1', 'rtf': '0.104'}, : 100%|██████████| 1/1 [00:00<00:00, 1.86it/s]
rtf_avg: 0.104: 100%|██████████| 1/1 [00:00<00:00, 1.86it/s]
rtf_avg: 0.096, time_speech: 5.616, time_escape: 0.540: 100%|██████████| 1/1 [00:00<00:00, 1.77it/s]
开放时间早上9点至下午5点。
Process finished with exit code 0
https://github.com/microsoft/VibeASR.cpp
https://huggingface.co/microsoft/VibeVoice-ASR-BitNet
在线体验：https://huggingface.co/spaces/microsoft/vibevoice-asr-bitnet-demo
https://github.com/Uberi/speech_recognition
pip install SpeechRecognition
麦克风相关
brew install portaudio pip install pyaudio
运行下面命令授权访问麦克风
neo@MacBook-Pro-Neo ~ % python3 -m speech_recognition
import speech_recognition as sr
for index, name in enumerate(sr.Microphone.list_microphone_names()):
print("Microphone with name \"{1}\" found for `Microphone(device_index={0})`".format(index, name))
输出结果
neo@MacBook-Pro-Neo ~/workspace/python/speech % python3 microphone.py Microphone with name "Built-in Microphone" found for `Microphone(device_index=0)` Microphone with name "Built-in Output" found for `Microphone(device_index=1)`
指定麦克风设备
import speech_recognition as sr print(sr.__version__) # just to print the version not required r = sr.Recognizer() mic = sr.Microphone(device_index=1) #my device index is 1, you have to put your device index
噪声抑制
import speech_recognition as sr
print(sr.__version__) # just to print the version not required
r = sr.Recognizer()
my_mic = sr.Microphone(device_index=1) #my device index is 1, you have to put your device index
with my_mic as source:
print("Say now!!!!")
r.adjust_for_ambient_noise(source) #reduce noise
audio = r.listen(source) #take voice input from the microphone
print(r.recognize_google(audio)) #to print voice into text
https://deepspeech.readthedocs.io/en/latest/index.html
# Install DeepSpeech pip3 install deepspeech # Download pre-trained English model files curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.pbmm curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/deepspeech-0.9.3-models.scorer # Download example audio files curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/audio-0.9.3.tar.gz tar xvf audio-0.9.3.tar.gz # Transcribe an audio file deepspeech --model deepspeech-0.9.3-models.pbmm --scorer deepspeech-0.9.3-models.scorer --audio audio/2830-3980-0043.wav
docker run -it kaldiasr/kaldi:latest bash
docker run -it --runtime=nvidia kaldiasr/kaldi:gpu-latest bash
docker run -it kaldiasr/kaldi:latest bash
PocketSphinx默认仅支持英文识别，中文需要下载 语言模型文件 ，Mandarin 为中文普通话。
brew install swig brew install pocketsphinx pip install PocketSphinx
从文件识别
import speech_recognition as sr
# obtain audio from the file
recognizer = sr.Recognizer()
audioFile = sr.AudioFile(r"english.wav")
with audioFile as source:
audio = recognizer.record(source)
# recognize speech using Sphinx
try:
print("Sphinx thinks you said: " + recognizer.recognize_sphinx(audio))
except sr.UnknownValueError:
print("Sphinx could not understand audio")
except sr.RequestError as e:
print("Sphinx error; {0}".format(e))
从麦克风识别
#!/usr/bin/env python3
import speech_recognition as sr
print(sr.__version__)
for index, name in enumerate(sr.Microphone.list_microphone_names()):
print("Microphone with name \"{1}\" found for `Microphone(device_index={0})`".format(index, name))
# obtain audio from the microphone
r = sr.Recognizer()
with sr.Microphone() as source:
print("Say something!")
audio = r.listen(source)
# recognize speech using Sphinx
try:
print("Sphinx thinks you said: " + r.recognize_sphinx(audio))
except sr.UnknownValueError:
print("Sphinx could not understand audio")
except sr.RequestError as e:
print("Sphinx error; {0}".format(e))