录制和识别来自 URL 的音乐
Record and Recognize music from URL
我在 python DeJavu 中使用开源音频指纹识别平台，它可以识别来自磁盘和麦克风的音乐。
我已经测试了从磁盘的识别，这是惊人的。 100% 准确率。
我寻求有关如何添加 class "BroadcastRecognizer" 的帮助
这将从 URL 在线流示例在线广播中识别音乐 [http://bbcmedia.ic.llnwd.net/stream/bbcmedia_radio1_mf_p]
因为广播流里的音乐是不断变化的，想设置为每10秒识别一次。
这是recognize.py
import dejavu.fingerprint as fingerprint
import dejavu.decoder as decoder
import numpy as np
import pyaudio
import time
class BaseRecognizer(object):
def __init__(self, dejavu):
self.dejavu = dejavu
self.Fs = fingerprint.DEFAULT_FS
def _recognize(self, *data):
matches = []
for d in data:
matches.extend(self.dejavu.find_matches(d, Fs=self.Fs))
return self.dejavu.align_matches(matches)
def recognize(self):
pass # base class does nothing
class FileRecognizer(BaseRecognizer):
def __init__(self, dejavu):
super(FileRecognizer, self).__init__(dejavu)
def recognize_file(self, filename):
frames, self.Fs, file_hash = decoder.read(filename, self.dejavu.limit)
t = time.time()
match = self._recognize(*frames)
t = time.time() - t
if match:
match['match_time'] = t
return match
def recognize(self, filename):
return self.recognize_file(filename)
class MicrophoneRecognizer(BaseRecognizer):
default_chunksize = 8192
default_format = pyaudio.paInt16
default_channels = 2
default_samplerate = 44100
def __init__(self, dejavu):
super(MicrophoneRecognizer, self).__init__(dejavu)
self.audio = pyaudio.PyAudio()
self.stream = None
self.data = []
self.channels = MicrophoneRecognizer.default_channels
self.chunksize = MicrophoneRecognizer.default_chunksize
self.samplerate = MicrophoneRecognizer.default_samplerate
self.recorded = False
def start_recording(self, channels=default_channels,
samplerate=default_samplerate,
chunksize=default_chunksize):
self.chunksize = chunksize
self.channels = channels
self.recorded = False
self.samplerate = samplerate
if self.stream:
self.stream.stop_stream()
self.stream.close()
self.stream = self.audio.open(
format=self.default_format,
channels=channels,
rate=samplerate,
input=True,
frames_per_buffer=chunksize,
)
self.data = [[] for i in range(channels)]
def process_recording(self):
data = self.stream.read(self.chunksize)
nums = np.fromstring(data, np.int16)
for c in range(self.channels):
self.data[c].extend(nums[c::self.channels])
def stop_recording(self):
self.stream.stop_stream()
self.stream.close()
self.stream = None
self.recorded = True
def recognize_recording(self):
if not self.recorded:
raise NoRecordingError("Recording was not complete/begun")
return self._recognize(*self.data)
def get_recorded_time(self):
return len(self.data[0]) / self.rate
def recognize(self, seconds=10):
self.start_recording()
for i in range(0, int(self.samplerate / self.chunksize
* seconds)):
self.process_recording()
self.stop_recording()
return self.recognize_recording()
class NoRecordingError(Exception):
pass
这是dejavu.py
import os``
import sys
import json
import warnings
import argparse
from dejavu import Dejavu
from dejavu.recognize import FileRecognizer
from dejavu.recognize import MicrophoneRecognizer
from argparse import RawTextHelpFormatter
warnings.filterwarnings("ignore")
DEFAULT_CONFIG_FILE = "dejavu.cnf.SAMPLE"
def init(configpath):
"""
Load config from a JSON file
"""
try:
with open(configpath) as f:
config = json.load(f)
except IOError as err:
print("Cannot open configuration: %s. Exiting" % (str(err)))
sys.exit(1)
# create a Dejavu instance
return Dejavu(config)
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description="Dejavu: Audio Fingerprinting library",
formatter_class=RawTextHelpFormatter)
parser.add_argument('-c', '--config', nargs='?',
help='Path to configuration file\n'
'Usages: \n'
'--config /path/to/config-file\n')
parser.add_argument('-f', '--fingerprint', nargs='*',
help='Fingerprint files in a directory\n'
'Usages: \n'
'--fingerprint /path/to/directory extension\n'
'--fingerprint /path/to/directory')
parser.add_argument('-r', '--recognize', nargs=2,
help='Recognize what is '
'playing through the microphone\n'
'Usage: \n'
'--recognize mic number_of_seconds \n'
'--recognize file path/to/file \n')
args = parser.parse_args()
if not args.fingerprint and not args.recognize:
parser.print_help()
sys.exit(0)
config_file = args.config
if config_file is None:
config_file = DEFAULT_CONFIG_FILE
# print "Using default config file: %s" % (config_file)
djv = init(config_file)
if args.fingerprint:
# Fingerprint all files in a directory
if len(args.fingerprint) == 2:
directory = args.fingerprint[0]
extension = args.fingerprint[1]
print("Fingerprinting all .%s files in the %s directory"
% (extension, directory))
djv.fingerprint_directory(directory, ["." + extension], 4)
elif len(args.fingerprint) == 1:
filepath = args.fingerprint[0]
if os.path.isdir(filepath):
print("Please specify an extension if you'd like to fingerprint a directory!")
sys.exit(1)
djv.fingerprint_file(filepath)
elif args.recognize:
# Recognize audio source
song = None
source = args.recognize[0]
opt_arg = args.recognize[1]
if source in ('mic', 'microphone'):
song = djv.recognize(MicrophoneRecognizer, seconds=opt_arg)
elif source == 'file':
song = djv.recognize(FileRecognizer, opt_arg)
print(song)
sys.exit(0)
我仍然认为您需要一个离散的 "piece" 音频，因此您需要一个开头和一个结尾。
对于它的价值，从这样的东西开始，它记录了 10 秒的音频，然后你可以根据你的指纹记录进行测试。
注意：这是针对 python 2 的，因此您必须在 python 3
上将其编辑为 运行
import time, sys
import urllib2
url = "http://bbcmedia.ic.llnwd.net/stream/bbcmedia_radio1_mf_p"
print ("Connecting to "+url)
response = urllib2.urlopen(url, timeout=10.0)
fname = "Sample"+str(time.clock())[2:]+".wav"
f = open(fname, 'wb')
block_size = 1024
print ("Recording roughly 10 seconds of audio Now - Please wait")
limit = 10
start = time.time()
while time.time() - start < limit:
try:
audio = response.read(block_size)
if not audio:
break
f.write(audio)
sys.stdout.write('.')
sys.stdout.flush()
except Exception as e:
print ("Error "+str(e))
f.close()
sys.stdout.flush()
print("")
print ("10 seconds from "+url+" have been recorded in "+fname)
#
# here run the finger print test to identify the audio recorded
# using the sample you have downloaded in the file "fname"
#
我在 python DeJavu 中使用开源音频指纹识别平台，它可以识别来自磁盘和麦克风的音乐。 我已经测试了从磁盘的识别，这是惊人的。 100% 准确率。
我寻求有关如何添加 class "BroadcastRecognizer" 的帮助 这将从 URL 在线流示例在线广播中识别音乐 [http://bbcmedia.ic.llnwd.net/stream/bbcmedia_radio1_mf_p] 因为广播流里的音乐是不断变化的，想设置为每10秒识别一次。
这是recognize.py
import dejavu.fingerprint as fingerprint
import dejavu.decoder as decoder
import numpy as np
import pyaudio
import time
class BaseRecognizer(object):
def __init__(self, dejavu):
self.dejavu = dejavu
self.Fs = fingerprint.DEFAULT_FS
def _recognize(self, *data):
matches = []
for d in data:
matches.extend(self.dejavu.find_matches(d, Fs=self.Fs))
return self.dejavu.align_matches(matches)
def recognize(self):
pass # base class does nothing
class FileRecognizer(BaseRecognizer):
def __init__(self, dejavu):
super(FileRecognizer, self).__init__(dejavu)
def recognize_file(self, filename):
frames, self.Fs, file_hash = decoder.read(filename, self.dejavu.limit)
t = time.time()
match = self._recognize(*frames)
t = time.time() - t
if match:
match['match_time'] = t
return match
def recognize(self, filename):
return self.recognize_file(filename)
class MicrophoneRecognizer(BaseRecognizer):
default_chunksize = 8192
default_format = pyaudio.paInt16
default_channels = 2
default_samplerate = 44100
def __init__(self, dejavu):
super(MicrophoneRecognizer, self).__init__(dejavu)
self.audio = pyaudio.PyAudio()
self.stream = None
self.data = []
self.channels = MicrophoneRecognizer.default_channels
self.chunksize = MicrophoneRecognizer.default_chunksize
self.samplerate = MicrophoneRecognizer.default_samplerate
self.recorded = False
def start_recording(self, channels=default_channels,
samplerate=default_samplerate,
chunksize=default_chunksize):
self.chunksize = chunksize
self.channels = channels
self.recorded = False
self.samplerate = samplerate
if self.stream:
self.stream.stop_stream()
self.stream.close()
self.stream = self.audio.open(
format=self.default_format,
channels=channels,
rate=samplerate,
input=True,
frames_per_buffer=chunksize,
)
self.data = [[] for i in range(channels)]
def process_recording(self):
data = self.stream.read(self.chunksize)
nums = np.fromstring(data, np.int16)
for c in range(self.channels):
self.data[c].extend(nums[c::self.channels])
def stop_recording(self):
self.stream.stop_stream()
self.stream.close()
self.stream = None
self.recorded = True
def recognize_recording(self):
if not self.recorded:
raise NoRecordingError("Recording was not complete/begun")
return self._recognize(*self.data)
def get_recorded_time(self):
return len(self.data[0]) / self.rate
def recognize(self, seconds=10):
self.start_recording()
for i in range(0, int(self.samplerate / self.chunksize
* seconds)):
self.process_recording()
self.stop_recording()
return self.recognize_recording()
class NoRecordingError(Exception):
pass
这是dejavu.py
import os``
import sys
import json
import warnings
import argparse
from dejavu import Dejavu
from dejavu.recognize import FileRecognizer
from dejavu.recognize import MicrophoneRecognizer
from argparse import RawTextHelpFormatter
warnings.filterwarnings("ignore")
DEFAULT_CONFIG_FILE = "dejavu.cnf.SAMPLE"
def init(configpath):
"""
Load config from a JSON file
"""
try:
with open(configpath) as f:
config = json.load(f)
except IOError as err:
print("Cannot open configuration: %s. Exiting" % (str(err)))
sys.exit(1)
# create a Dejavu instance
return Dejavu(config)
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description="Dejavu: Audio Fingerprinting library",
formatter_class=RawTextHelpFormatter)
parser.add_argument('-c', '--config', nargs='?',
help='Path to configuration file\n'
'Usages: \n'
'--config /path/to/config-file\n')
parser.add_argument('-f', '--fingerprint', nargs='*',
help='Fingerprint files in a directory\n'
'Usages: \n'
'--fingerprint /path/to/directory extension\n'
'--fingerprint /path/to/directory')
parser.add_argument('-r', '--recognize', nargs=2,
help='Recognize what is '
'playing through the microphone\n'
'Usage: \n'
'--recognize mic number_of_seconds \n'
'--recognize file path/to/file \n')
args = parser.parse_args()
if not args.fingerprint and not args.recognize:
parser.print_help()
sys.exit(0)
config_file = args.config
if config_file is None:
config_file = DEFAULT_CONFIG_FILE
# print "Using default config file: %s" % (config_file)
djv = init(config_file)
if args.fingerprint:
# Fingerprint all files in a directory
if len(args.fingerprint) == 2:
directory = args.fingerprint[0]
extension = args.fingerprint[1]
print("Fingerprinting all .%s files in the %s directory"
% (extension, directory))
djv.fingerprint_directory(directory, ["." + extension], 4)
elif len(args.fingerprint) == 1:
filepath = args.fingerprint[0]
if os.path.isdir(filepath):
print("Please specify an extension if you'd like to fingerprint a directory!")
sys.exit(1)
djv.fingerprint_file(filepath)
elif args.recognize:
# Recognize audio source
song = None
source = args.recognize[0]
opt_arg = args.recognize[1]
if source in ('mic', 'microphone'):
song = djv.recognize(MicrophoneRecognizer, seconds=opt_arg)
elif source == 'file':
song = djv.recognize(FileRecognizer, opt_arg)
print(song)
sys.exit(0)
我仍然认为您需要一个离散的 "piece" 音频，因此您需要一个开头和一个结尾。
对于它的价值，从这样的东西开始，它记录了 10 秒的音频，然后你可以根据你的指纹记录进行测试。
注意：这是针对 python 2 的，因此您必须在 python 3
import time, sys
import urllib2
url = "http://bbcmedia.ic.llnwd.net/stream/bbcmedia_radio1_mf_p"
print ("Connecting to "+url)
response = urllib2.urlopen(url, timeout=10.0)
fname = "Sample"+str(time.clock())[2:]+".wav"
f = open(fname, 'wb')
block_size = 1024
print ("Recording roughly 10 seconds of audio Now - Please wait")
limit = 10
start = time.time()
while time.time() - start < limit:
try:
audio = response.read(block_size)
if not audio:
break
f.write(audio)
sys.stdout.write('.')
sys.stdout.flush()
except Exception as e:
print ("Error "+str(e))
f.close()
sys.stdout.flush()
print("")
print ("10 seconds from "+url+" have been recorded in "+fname)
#
# here run the finger print test to identify the audio recorded
# using the sample you have downloaded in the file "fname"
#