Updated README

README.md

@@ -50,7 +50,7 @@ audio_array, sr = librosa.load("path_to_audio.wav", sr=16000)
 
 ## Load model and feature extractor
 model = AutoModelForAudioClassification.from_pretrained("alkiskoudounas/hubert-base-slurp")
-feature_extractor = AutoFeatureExtractor.from_pretrained("alkiskoudounas/hubert-base-slurp")
+feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/hubert-base-ls960")
 
 ## Extract features
 inputs = feature_extractor(audio_array.squeeze(), sampling_rate=feature_extractor.sampling_rate, padding=True, return_tensors="pt")
@@ -68,7 +68,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 128
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 - warmup_steps: 3000
@@ -77,7 +77,7 @@ The following hyperparameters were used during training:
 ## Framework versions
 
 - Datasets 3.2.0
-- Pytorch 2.1.2+cu121
+- Pytorch 2.1.2
 - Tokenizers 0.20.3
 - Transformers 4.45.2