Update README.md

README.md

@@ -62,16 +62,8 @@ conda create --name antideepfake python==3.9.0
 conda activate antideepfake
 conda install pip==24.0
 
-### Install Fariseq ###
-# fairseq 0.10.2 on pip does not work
-git clone https://github.com/pytorch/fairseq
-cd fairseq
-# checkout this specific commit. Latest commit does not work
-git checkout 862efab86f649c04ea31545ce28d13c59560113d
-pip install --editable .
-
-### Install other packages ###
-pip install huggingface-hub==0.31.1 safetensors==0.5.3 soundfile==0.13.1 numpy==1.21.2
+### Install packages ###
+pip install huggingface-hub==0.31.1 fairseq==0.12.2 safetensors==0.5.3 soundfile==0.13.1
 ```
 
 🚀 Inference:
@@ -80,7 +72,7 @@ import os
 import urllib.request
 import torch
 import torchaudio
-import fairseq
+from fairseq.models.wav2vec import Wav2Vec2Model, Wav2Vec2Config
 from huggingface_hub import PyTorchModelHubMixin
 
 # This is the only part of the script you need to modify.
@@ -92,26 +84,31 @@ audio_formats = (".mp3", ".wav", ".flac", ".m4a")
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 print(f"Using device: {device}")
 
-# === Download Fairseq checkpoint if not present ===
-# The downloaded checkpoint is used for building front-end architecture,
-# its weights will be replaced by the model.safetensors file in this repo.
-ssl_path = "xlsr2_2B_1000k.pt"
-ssl_url = "https://dl.fbaipublicfiles.com/fairseq/wav2vec/xlsr2_2B_1000k.pt"
-
-if not os.path.exists(ssl_path):
-    print(f"Downloading checkpoint to {ssl_path}...")
-    urllib.request.urlretrieve(ssl_url, ssl_path)
-    print("Download complete.")
-else:
-    print(f"{ssl_path} already exists. Skipping download.")
-
 # === Wrapper for the SSL model ===
 class SSLModel(torch.nn.Module):
     def __init__(self):
         super().__init__()
-        # The downloaded .pt file is used here
-        model, _, _ = fairseq.checkpoint_utils.load_model_ensemble_and_task([ssl_path])
-        self.model = model[0].to(device)
+        # Model config used to build SSL architecture
+        cfg = Wav2Vec2Config(
+            quantize_targets=True,
+            extractor_mode="layer_norm",
+            layer_norm_first=True,
+            final_dim=1024,
+            latent_temp=(2.0, 0.1, 0.999995),
+            encoder_layerdrop=0.0,
+            dropout_input=0.0,
+            dropout_features=0.0,
+            dropout=0.0,
+            attention_dropout=0.0,
+            conv_bias=True,
+            encoder_layers=48,
+            encoder_embed_dim=1920,
+            encoder_ffn_embed_dim=7680,
+            encoder_attention_heads=16,
+            feature_grad_mult=1.0,
+        )
+        # Initialize SSL model with random weights
+        self.model = Wav2Vec2Model(cfg)
 
     def extract_feat(self, input_data):
         # If input has shape (B, T, 1), squeeze the last dim