تعلم الآلة للصوت والكلام

import librosa
import numpy as np
import matplotlib.pyplot as plt

class="tok-comment"># ── class="tok-num">1. Load audio ─────────────────────────────────────────────────────────────
y, sr = librosa.load(class="tok-str">"speech.wav", sr=class="tok-num">16000)   class="tok-comment"># resample to 16kHz
print(fclass="tok-str">"Duration: {len(y)/sr:.2f}s, Sample rate: {sr}Hz")

class="tok-comment"># ── class="tok-num">2. Waveform to spectrogram ────────────────────────────────────────────────
D = librosa.stft(y, n_fft=class="tok-num">400, hop_length=class="tok-num">160, win_length=class="tok-num">400)
spectrogram = np.abs(D)**class="tok-num">2               class="tok-comment"># power spectrogram (magnitude²)
S_db = librosa.power_to_db(spectrogram, ref=np.max)  class="tok-comment"># decibel scale

class="tok-comment"># ── class="tok-num">3. Mel spectrogram ────────────────────────────────────────────────────────
S_mel = librosa.feature.melspectrogram(
    y=y, sr=sr,
    n_fft=class="tok-num">400,
    hop_length=class="tok-num">160,        class="tok-comment"># 10ms stride at 16kHz
    win_length=class="tok-num">400,        class="tok-comment"># 25ms window at 16kHz
    n_mels=class="tok-num">80,             class="tok-comment"># class="tok-num">80 Mel bins (Whisper standard)
    fmin=class="tok-num">50, fmax=class="tok-num">8000,    class="tok-comment"># filter between 50Hz and 8kHz
)
log_mel = librosa.power_to_db(S_mel, ref=np.max)
print(fclass="tok-str">"Log-mel shape: {log_mel.shape}")   class="tok-comment"># (class="tok-num">80, T)

class="tok-comment"># ── class="tok-num">4. MFCC ──────────────────────────────────────────────────────────────────
mfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=class="tok-num">13, n_mels=class="tok-num">80)
mfcc_delta  = librosa.feature.delta(mfcc)    class="tok-comment"># velocity: change over time
mfcc_delta2 = librosa.feature.delta(mfcc, order=class="tok-num">2)  class="tok-comment"># acceleration

features = np.vstack([mfcc, mfcc_delta, mfcc_delta2])  class="tok-comment"># class="tok-num">39-dim feature vector
print(fclass="tok-str">"MFCC + deltas shape: {features.shape}")  class="tok-comment"># (class="tok-num">39, T)

class="tok-comment"># ── class="tok-num">5. Audio classification with CNN ─────────────────────────────────────────
import torch, torch.nn as nn

class AudioCNN(nn.Module):
    def __init__(self, n_classes: int):
        super().__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(class="tok-num">1, class="tok-num">32, kernel_size=class="tok-num">3, padding=class="tok-num">1), nn.ReLU(),
            nn.MaxPool2d(class="tok-num">2),
            nn.Conv2d(class="tok-num">32, class="tok-num">64, kernel_size=class="tok-num">3, padding=class="tok-num">1), nn.ReLU(),
            nn.MaxPool2d(class="tok-num">2),
            nn.Conv2d(class="tok-num">64, class="tok-num">128, kernel_size=class="tok-num">3, padding=class="tok-num">1), nn.ReLU(),
            nn.AdaptiveAvgPool2d((class="tok-num">4, class="tok-num">4)),    class="tok-comment"># global average pool to fixed size
        )
        self.fc = nn.Sequential(
            nn.Linear(class="tok-num">128*class="tok-num">4*class="tok-num">4, class="tok-num">256), nn.ReLU(), nn.Dropout(class="tok-num">0.4),
            nn.Linear(class="tok-num">256, n_classes),
        )
    def forward(self, x):
        class="tok-comment"># x: (B, class="tok-num">1, n_mels, T) — log-mel as single-channel class="tok-str">"image"
        return self.fc(self.conv(x).flatten(class="tok-num">1))

model = AudioCNN(n_classes=class="tok-num">10)   class="tok-comment"># e.g., UrbanSound8K: class="tok-num">10 sound classes
x = torch.randn(class="tok-num">8, class="tok-num">1, class="tok-num">80, class="tok-num">128)  class="tok-comment"># batch of class="tok-num">8 audio clips, class="tok-num">80 mels, class="tok-num">128 frames
print(model(x).shape)            class="tok-comment"># (class="tok-num">8, class="tok-num">10)

class="tok-comment"># ── class="tok-num">6. OpenAI Whisper (speech-to-text) ───────────────────────────────────────
class="tok-comment"># pip install openai-whisper
import whisper
model_w = whisper.load_model(class="tok-str">"base")          class="tok-comment"># 74M params
result  = model_w.transcribe(class="tok-str">"speech.wav")
print(result[class="tok-str">"text"])                          class="tok-comment"># full transcript
print(result[class="tok-str">"language"])                      class="tok-comment"># detected language

class="tok-comment"># Timestamps for each word
result_ts = model_w.transcribe(class="tok-str">"speech.wav", word_timestamps=True)
for seg in result_ts[class="tok-str">"segments"]:
    print(fclass="tok-str">"[{seg['start']:.2f}s → {seg['end']:.2f}s] {seg['text']}")