def __eq__(self, other):
"""Return whether two objects are equal.
"""
if not AudioSegment.__eq__(self, other):
return False
if self._transcript != other._transcript:
return False
return True
def transform_audio(self, audio_segment):
"""Add impulse response effect.
Note that this is an in-place transformation.
:param audio_segment: Audio segment to add effects to.
:type audio_segment: AudioSegmenet|SpeechSegment
"""
impulse_json = self._rng.sample(self._impulse_manifest, 1)[0]
impulse_segment = AudioSegment.from_file(impulse_json['audio_filepath'])
audio_segment.convolve(impulse_segment, allow_resample=True)
def from_file(cls, filepath, transcript):
"""Create speech segment from audio file and corresponding transcript.
:param filepath: Filepath or file object to audio file.
:type filepath: basestring|file
:param transcript: Transcript text for the speech.
:type transript: basestring
:return: Speech segment instance.
:rtype: SpeechSegment
"""
audio = AudioSegment.from_file(filepath)
return cls(audio.samples, audio.sample_rate, transcript)
def from_file(cls, filepath, transcript):
"""从音频文件和相应的文本创建语音片段
:param filepath: 音频文件路径
:type filepath: str|file
:param transcript: 音频文件对应的文本
:type transript: str
:return: Speech segment instance.
:rtype: SpeechSegment
"""
audio = AudioSegment.from_file(filepath)
return cls(audio.samples, audio.sample_rate, transcript)
def make_silence(cls, duration, sample_rate):
"""创建指定安静音频长度和采样率的SpeechSegment实例，音频文件对应的文本将为空字符串。
:param duration: 安静音频的时间，单位秒
:type duration: float
:param sample_rate: 音频采样率
:type sample_rate: float
:return: 安静音频SpeechSegment实例
:rtype: SpeechSegment
"""
audio = AudioSegment.make_silence(duration, sample_rate)
return cls(audio.samples, audio.sample_rate, "")
def _compute_mean_std(self, manifest_path, featurize_func, num_samples):
"""从随机抽样的实例中计算均值和标准值"""
manifest = read_manifest(manifest_path)
sampled_manifest = self._rng.sample(manifest, num_samples)
features = []
for instance in tqdm(sampled_manifest):
features.append(
featurize_func(
AudioSegment.from_file(instance["audio_filepath"])))
features = np.hstack(features)
self._mean = np.mean(features, axis=1).reshape([-1, 1])
self._std = np.std(features, axis=1).reshape([-1, 1])
def _compute_mean_std(self, manifest_path, featurize_func, num_samples):
"""Compute mean and std from randomly sampled instances."""
manifest = read_manifest(manifest_path)
sampled_manifest = self._rng.sample(manifest, num_samples)
features = []
for instance in sampled_manifest:
features.append(
featurize_func(
AudioSegment.from_file(instance["audio_filepath"])))
features = np.hstack(features)
self._mean = np.mean(features, axis=1).reshape([-1, 1])
self._std = np.std(features, axis=1).reshape([-1, 1])
def from_bytes(cls, bytes, transcript):
"""从字节串和相应的文本创建语音片段
:param bytes: 包含音频样本的字节字符串
:type bytes: str
:param transcript: 音频文件对应的文本
:type transript: str
:return: Speech segment instance.
:rtype: Speech Segment
"""
audio = AudioSegment.from_bytes(bytes)
return cls(audio.samples, audio.sample_rate, transcript)
def make_silence(cls, duration, sample_rate):
"""Creates a silent speech segment of the given duration and
sample rate, transcript will be an empty string.
:param duration: Length of silence in seconds.
:type duration: float
:param sample_rate: Sample rate.
:type sample_rate: float
:return: Silence of the given duration.
:rtype: SpeechSegment
"""
audio = AudioSegment.make_silence(duration, sample_rate)
return cls(audio.samples, audio.sample_rate, "")
def from_bytes(cls, bytes, transcript):
"""Create speech segment from a byte string and corresponding
transcript.
:param bytes: Byte string containing audio samples.
:type bytes: str
:param transcript: Transcript text for the speech.
:type transript: basestring
:return: Speech segment instance.
:rtype: Speech Segment
"""
audio = AudioSegment.from_bytes(bytes)
return cls(audio.samples, audio.sample_rate, transcript)
def from_bytes(cls, bytes, transcript, **soundfile_options):
"""Create speech segment from a byte string and corresponding
transcript.
:param bytes: Byte string containing audio samples.
:type bytes: str
:param transcript: Transcript text for the speech.
:type transript: basestring
:param soundfile_options: Options for opening with soundfile library.
:type soundfile_options: **kwargs
:return: Speech segment instance.
:rtype: Speech Segment
"""
audio = AudioSegment.from_bytes(bytes, **soundfile_options)
return cls(audio.samples, audio.sample_rate, transcript)
def slice_from_file(cls, filepath, transcript, start=None, end=None):
"""只加载一小部分SpeechSegment，而不需要将整个文件加载到内存中，这是非常浪费的。
:param filepath:文件路径或文件对象到音频文件
:type filepath: str|file
:param start: 开始时间，单位为秒。如果start是负的，则它从末尾开始计算。如果没有提供，这个函数将从最开始读取。
:type start: float
:param end: 结束时间，单位为秒。如果end是负的，则它从末尾开始计算。如果没有提供，默认的行为是读取到文件的末尾。
:type end: float
:param transcript: 音频文件对应的文本，如果没有提供，默认值是一个空字符串。
:type transript: str
:return: SpeechSegment实例
:rtype: SpeechSegment
"""
audio = AudioSegment.slice_from_file(filepath, start, end)
return cls(audio.samples, audio.sample_rate, transcript)
def transform_audio(self, audio_segment):
"""Add background noise audio.
Note that this is an in-place transformation.
:param audio_segment: Audio segment to add effects to.
:type audio_segment: AudioSegmenet|SpeechSegment
"""
noise_json = self._rng.sample(self._noise_manifest, 1)[0]
if noise_json['duration'] >= audio_segment.duration:
diff_duration = noise_json['duration'] - audio_segment.duration
start = self._rng.uniform(0, diff_duration)
end = start + audio_segment.duration
noise_segment = AudioSegment.slice_from_file(
noise_json['audio_filepath'], start=start, end=end)
snr_dB = self._rng.uniform(self._min_snr_dB, self._max_snr_dB)
audio_segment.add_noise(noise_segment,
snr_dB,
allow_downsampling=True,
rng=self._rng)
def slice_from_file(cls, filepath, transcript, start=None, end=None):
"""Loads a small section of an speech without having to load
the entire file into the memory which can be incredibly wasteful.
:param filepath: Filepath or file object to audio file.
:type filepath: basestring|file
:param start: Start time in seconds. If start is negative, it wraps
around from the end. If not provided, this function
reads from the very beginning.
:type start: float
:param end: End time in seconds. If end is negative, it wraps around
from the end. If not provided, the default behvaior is
to read to the end of the file.
:type end: float
:param transcript: Transcript text for the speech. if not provided,
the defaults is an empty string.
:type transript: basestring
:return: SpeechSegment instance of the specified slice of the input
speech file.
:rtype: SpeechSegment
"""
audio = AudioSegment.slice_from_file(filepath, start, end)
return cls(audio.samples, audio.sample_rate, transcript)
def __getitem__(self, idx):
instance = self.sampled_manifest[idx]
# 获取音频特征
audio = AudioSegment.from_file(instance["audio_filepath"])
feature = self.audio_featurizer.featurize(audio)
return feature, 0
speed = random.randint(12, 12) / 10.
outputfile = path + '/' + name.split('.')[0] + "-" + str(
speed) + "-" + 'work.wav'
# audio = AudioSegment.from_file(w)
# audio.change_speed(speed)
# audio.to_wav_file(outputfile)
#
# outputfile1 = path + '/' + name.split('.')[0] + "-" + str(speed) + "-" + 'work1.wav'
# audio, sr1 = sf.read(w, dtype='float32')
# result_a = librosa.effects.time_stretch(audio, speed)
# librosa.output.write_wav(outputfile1, result_a, sr1)
noise_percent = 1
seq_length = 600
audio, sr1 = sf.read(w, dtype='float32')
if random.random() < noise_percent and seq_length > 0:
temp_audio = AudioSegment(audio, sr1)
audio_length = audio.shape[0]
max_length_ratio = int(
(float(audio_length) / (seq_length - 100) / sr1) * 10000)
min_length_ratio = int(
np.math.ceil((float(audio_length) / seq_length / sr1) * 10000))
temp_audio.change_speed(
random.randint(min_length_ratio, max_length_ratio) / 100.)
audio = temp_audio.samples
if random.random() < noise_percent:
if seq_length != -1:
max_length = seq_length * sr1 / 100
if audio.shape[0] < max_length:
bg = np.zeros((max_length, ))
rand_start = random.randint(0, max_length - audio.shape[0])
bg[rand_start:rand_start + audio.shape[0]] = audio
def __init__(self, samples, sample_rate, transcript):
AudioSegment.__init__(self, samples, sample_rate)
self._transcript = transcript