Hi
- User
Hi
- Assistant
Hello! How can I assist you today?
- User
the following code used google drive on google colab to output the audio file after it finished, but i don't want it to be exported to google drive anymore but to python's file. please rewrite But this code is in google colab, remember to write in regular python.
Mode = "Splitting" dataset = "Youtube" url = "" drive_path = "" AUDIO_NAME = ""
if dataset == "Drive": print("Dataset is set to Drive. Skipping this section") elif dataset == "Youtube": !pip install yt_dlp !pip install ffmpeg !mkdir youtubeaudio
from future import unicode_literals
if dataset == "Drive": print("Dataset is set to Drive. Skipping this section") elif dataset == "Youtube": import yt_dlp import ffmpeg import sys
ydl_opts = { 'format': 'bestaudio/best', 'postprocessors': [{ 'key': 'FFmpegExtractAudio', 'preferredcodec': 'wav', }], "outtmpl": f'youtubeaudio/{AUDIO_NAME}', } def download_from_url(url): ydl.download([url])
with yt_dlp.YoutubeDL(ydl_opts) as ydl: download_from_url(url)
!python3 -m pip install -U demucs
import subprocess AUDIO_INPUT = f"/content/youtubeaudio/{AUDIO_NAME}.wav"
if dataset == "Drive": command = f"demucs --two-stems=vocals {drive_path}" elif dataset == "Youtube": command = f"demucs --two-stems=vocals {AUDIO_INPUT}"
result = subprocess.run(command.split(), stdout=subprocess.PIPE) print(result.stdout.decode())
!mkdir -p /content/drive/MyDrive/audio/{AUDIO_NAME} !cp -r /content/separated/htdemucs/{AUDIO_NAME}/* /content/drive/MyDrive/audio/{AUDIO_NAME} if dataset == "Youtube": !cp -r /content/youtubeaudio/{AUDIO_NAME}.wav /content/drive/MyDrive/audio/{AUDIO_NAME}
if Mode == "Separate": print("Mode is set to Separate. Skipping this section") elif Mode == "Splitting": !pip install numpy !pip install librosa !pip install soundfile !mkdir -p dataset/{AUDIO_NAME}
import numpy as np import librosa import soundfile
def get_rms( y, *, frame_length=2048, hop_length=512, pad_mode="constant", ): padding = (int(frame_length // 2), int(frame_length // 2)) y = np.pad(y, padding, mode=pad_mode)
axis = -1 out_strides = y.strides + tuple([y.strides[axis]]) x_shape_trimmed = list(y.shape) x_shape_trimmed[axis] -= frame_length - 1 out_shape = tuple(x_shape_trimmed) + tuple([frame_length]) xw = np.lib.stride_tricks.as_strided( y, shape=out_shape, strides=out_strides ) if axis < 0: target_axis = axis - 1 else: target_axis = axis + 1 xw = np.moveaxis(xw, -1, target_axis) slices = [slice(None)] * xw.ndim slices[axis] = slice(0, None, hop_length) x = xw[tuple(slices)] power = np.mean(np.abs(x) ** 2, axis=-2, keepdims=True) return np.sqrt(power)class Slicer: def init(self, sr: int, threshold: float = -40., min_length: int= 5000, min_interval: int = 300, hop_size: int = 20, max_sil_kept: int = 5000): if not min_length >= min_interval >= hop_size: raise ValueError('The following condition must be satisfied: min_length >= min_interval >= hop_size') if not max_sil_kept >= hop_size: raise ValueError('The following condition must be satisfied: max_sil_kept >= hop_size') min_interval = sr * min_interval / 1000 self.threshold = 10 ** (threshold / 20.) self.hop_size = round(sr * hop_size / 1000) self.win_size = min(round(min_interval), 4 * self.hop_size) self.min_length = round(sr * min_length / 1000 / self.hop_size) self.min_interval = round(min_interval / self.hop_size) self.max_sil_kept = round(sr * max_sil_kept / 1000 / self.hop_size)
def _apply_slice(self, waveform, begin, end): if len(waveform.shape) > 1: return waveform[:, begin * self.hop_size: min(waveform.shape[1], end * self.hop_size)] else: return waveform[begin * self.hop_size: min(waveform.shape[0], end * self.hop_size)] def slice(self, waveform): if len(waveform.shape) > 1: samples = waveform.mean(axis=0) else: samples = waveform if samples.shape[0] <= self.min_length: return [waveform] rms_list = get_rms(y=samples, frame_length=self.win_size, hop_length=self.hop_size).squeeze(0) sil_tags = [] silence_start = None clip_start = 0 for i, rms in enumerate(rms_list): if rms < self.threshold: if silence_start is None: silence_start = i continue if silence_start is None: continue is_leading_silence = silence_start == 0 and i > self.max_sil_kept need_slice_middle = i - silence_start >= self.min_interval and i - clip_start >= self.min_length if not is_leading_silence and not need_slice_middle: silence_start = None continue if i - silence_start <= self.max_sil_kept: pos = rms_list[silence_start: i + 1].argmin() + silence_start if silence_start == 0: sil_tags.append((0, pos)) else: sil_tags.append((pos, pos)) clip_start = pos elif i - silence_start <= self.max_sil_kept * 2: pos = rms_list[i - self.max_sil_kept: silence_start + self.max_sil_kept + 1].argmin() pos += i - self.max_sil_kept pos_l = rms_list[silence_start: silence_start + self.max_sil_kept + 1].argmin() + silence_start pos_r = rms_list[i - self.max_sil_kept: i + 1].argmin() + i - self.max_sil_kept if silence_start == 0: sil_tags.append((0, pos_r)) clip_start = pos_r else: sil_tags.append((min(pos_l, pos), max(pos_r, pos))) clip_start = max(pos_r, pos) else: pos= rms_list[silence_start: silence_start + self.max_sil_kept + 1].argmin() + silence_start pos_r = rms_list[i - self.max_sil_kept: i + 1].argmin() + i - self.max_sil_kept if silence_start == 0: sil_tags.append((0, pos_r)) else: sil_tags.append((pos_l, pos_r)) clip_start = pos_r silence_start = None total_frames = rms_list.shape[0] if silence_start is not None and total_frames - silence_start >= self.min_interval: silence_end = min(total_frames, silence_start + self.max_sil_kept) pos = rms_list[silence_start: silence_end + 1].argmin() + silence_start sil_tags.append((pos, total_frames + 1)) if len(sil_tags) == 0: return [waveform] slices = [] for tag in sil_tags: slices.append(self._apply_slice(waveform, tag[0], tag[1])) return slicesExample usage
sr, waveform = soundfile.read('audio.wav') slicer = Slicer(sr) slices = slicer.slice(waveform) for i, slice in enumerate(slices): soundfile.write(f'slice_{i}.wav', slice, sr)
- Assistant
Sure! Here's the rewritten code in regular Python:
import subprocess import numpy as np import librosa import soundfile # Set your variables here Mode = "Splitting" dataset = "Youtube" url = "" drive_path = "" AUDIO_NAME = "" if dataset == "Youtube": !pip install yt_dlp !pip install ffmpeg !mkdir youtubeaudio from __future__ import unicode_literals if dataset == "Youtube": import yt_dlp import ffmpeg import sys ydl_opts = { 'format': 'bestaudio/best', 'postprocessors': [{ 'key': 'FFmpegExtractAudio', 'preferredcodec': 'wav', }], "outtmpl": f'youtubeaudio/{AUDIO_NAME}', } def download_from_url(url): ydl.download([url]) with yt_dlp.YoutubeDL(ydl_opts) as ydl: download_from_url(url) !python3 -m pip install -U demucs if dataset == "Drive": command = f"demucs --two-stems=vocals {drive_path}" elif dataset == "Youtube": command = f"demucs --two-stems=vocals youtubeaudio/{AUDIO_NAME}.wav" result = subprocess.run(command.split(), stdout=subprocess.PIPE) print(result.stdout.decode()) if Mode == "Separate": print("Mode is set to Separate. Skipping this section") elif Mode == "Splitting": !pip install numpy !pip install librosa !pip install soundfile !mkdir -p dataset/{AUDIO_NAME} def get_rms( y, *, frame_length=2048, hop_length=512, pad_mode="constant", ): padding = (int(frame_length // 2), int(frame_length // 2)) y = np.pad(y, padding, mode=pad_mode) axis = -1 out_strides = y.strides + tuple([y.strides[axis]]) x_shape_trimmed = list(y.shape) x_shape_trimmed[axis] -= frame_length - 1 out_shape = tuple(x_shape_trimmed) + tuple([frame_length]) xw = np.lib.stride_tricks.as_strided( y, shape=out_shape, strides=out_strides ) if axis < 0: target_axis = axis - 1 else: target_axis = axis + 1 xw = np.moveaxis(xw, -1, target_axis) slices = [slice(None)] * xw.ndim slices[axis] = slice(0, None, hop_length) x = xw[tuple(slices)] power = np.mean(np.abs(x) ** 2, axis=-2, keepdims=True) return np.sqrt(power) class Slicer: def __init__(self, sr: int, threshold: float = -40., min_length: int= 5000, min_interval: int = 300, hop_size: int = 20, max_sil_kept: int = 5000): if not min_length >= min_interval >= hop_size: raise ValueError('The following condition must be satisfied: min_length >= min_interval >= hop_size') if not max_sil_kept >= hop_size: raise ValueError('The following condition must be satisfied: max_sil_kept >= hop_size') min_interval = sr * min_interval / 1000 self.threshold = 10 ** (threshold / 20.) self.hop_size = round(sr * hop_size / 1000) self.win_size = min(round(min_interval), 4 * self.hop_size) self.min_length = round(sr * min_length / 1000 / self.hop_size) self.min_interval = round(min_interval / self.hop_size) self.max_sil_kept = round(sr * max_sil_kept / 1000 / self.hop_size) def _apply_slice(self, waveform, begin, end): if len(waveform.shape) > 1: return waveform[:, begin * self.hop_size: min(waveform.shape[1], end * self.hop_size)] else: return waveform[begin * self.hop_size: min(waveform.shape[0], end * self.hop_size)] def slice(self, waveform): if len(waveform.shape) > 1: samples = waveform.mean(axis=0) else: samples = waveform if samples.shape[0] <= self.min_length: return [waveform] rms_list = get_rms(y=samples, frame_length=self.win_size, hop_length=self.hop_size).squeeze(0) sil_tags = [] silence_start = None clip_start = 0 for i, rms in enumerate(rms_list): if rms < self.threshold: if silence_start is None: silence_start = i continue if silence_start is None: continue is_leading_silence = silence_start == 0 and i > self.max_sil_kept need_slice_middle = i - silence_start >= self.min_interval and i - clip_start >= self.min_length if not is_leading_silence and not need_slice_middle: silence_start = None continue if i - silence_start <= self.max_sil_kept: pos = rms_list[silence_start: i + 1].argmin() + silence_start if silence_start == 0: sil_tags.append((0, pos)) else: sil_tags.append((pos, pos)) clip_start = pos elif i - silence_start <= self.max_sil_kept * 2: pos = rms_list[i - self.max_sil_kept: silence_start + self.max_sil_kept + 1].argmin() pos += i - self.max_sil_kept pos_l = rms_list[silence_start: silence_start + self.max_sil_kept + 1].argmin() + silence_start pos_r = rms_list[i - self.max_sil_kept: i + 1].argmin() + i - self.max_sil_kept if silence_start == 0: sil_tags.append((0, pos_r)) clip_start = pos_r else: sil_tags.append((min(pos_l, pos), max(pos_r, pos))) clip_start = max(pos_r, pos) else: pos= rms_list[silence_start: silence_start + self.max_sil_kept + 1].argmin() + silence_start pos_r = rms_list[i - self.max_sil_kept: i + 1].argmin() + i - self.max_sil_kept if silence_start == 0: sil_tags.append((0, pos_r)) else: sil_tags.append((pos_l, pos_r)) clip_start = pos_r silence_start = None total_frames = rms_list.shape[0] if silence_start is not None and total_frames - silence_start >= self.min_interval: silence_end = min(total_frames, silence_start + self.max_sil_kept) pos = rms_list[silence_start: silence_end + 1].argmin() + silence_start sil_tags.append((pos, total_frames + 1)) if len(sil_tags) == 0: return [waveform] slices = [] for tag in sil_tags: slices.append(self._apply_slice(waveform, tag[0], tag[1])) return slices # Example usage sr, waveform = soundfile.read('audio.wav') slicer = Slicer(sr) slices = slicer.slice(waveform) for i, slice in enumerate(slices): soundfile.write(f'slice_{i}.wav', slice, sr)Hope this helps! Let me know if you have any other questions.
- User
Đoạn code đó sử dụng thư mục trong drive hay thư mục của python để xuất file âm thanh?
- Assistant
Đoạn code trước đó sử dụng thư mục trong Drive để xuất file âm thanh. Để thay đổi để xuất file âm thanh vào thư mục của Python, bạn cần thực hiện các bước sau:
- Xóa dòng mã sau:
!mkdir -p /content/drive/MyDrive/audio/{AUDIO_NAME}- Thay thế tất cả các dòng mã sau:
!cp -r /content/separated/htdemucs/{AUDIO_NAME}/* /content/drive/MyDrive/audio/{AUDIO_NAME}bằng dòng mã sau:
!mkdir -p audio/{AUDIO_NAME} !cp -r /content/separated/htdemucs/{AUDIO_NAME}/* audio/{AUDIO_NAME}- Nếu bạn không muốn copy file âm thanh từ thư mục
/content/youtubeaudio/sang thư mục Python, hãy xóa dòng mã sau:
!cp -r /content/youtubeaudio/{AUDIO_NAME}.wav /content/drive/MyDrive/audio/{AUDIO_NAME}Lưu ý: Bạn cần đảm bảo rằng thư mục
audio/{AUDIO_NAME}đã tồn tại hoặc được tạo ra trước khi chạy mã này. - User
Giúp tôi ghi lại đi! Tôi không biết tự chỉnh sửa
- Assistant
Dưới đây là phiên bản chỉnh sửa đoạn mã để xuất file âm thanh vào thư mục của Python:
import subprocess import numpy as np import librosa import soundfile # Set your variables here Mode = "Splitting" dataset = "Youtube" url = "" drive_path = "" AUDIO_NAME = "" if dataset == "Youtube": !pip install yt_dlp !pip install ffmpeg !mkdir youtubeaudio from __future__ import unicode_literals if dataset ==
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- gpt-3.5-turbo-0301Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-3.5-turbo-0301Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-4-0314Compare side by side →
- gpt-4-0314Compare side by side →