Commit History
-
Update README.md
Verified signature6855a95
-
Update README.md
Verified signature6250a60 -
Update README.md
Verified signaturereadme updated4c74016 -
Update README.md
Verified signature4431555 -
Update README.md
Verified signature0aff5d9 -
Delete requirements.txt
Verified signatureno needed736d0e4 -
Delete app.py
Verified signatureno needed0df934d -
Upload 7 files
Verified signatureuploading model files in current location.ad9cb9d -
Delete wav2vec2_finetuned_model
Verified signaturei am deleting this folder because hugging-face can't read subfoldersaa9fc91 -
Create app.py
Verified signature702aa95 -
Create requirements.txt
Verified signature5a5b5ec -
Inference
Verified signatureimport torch from transformers import Wav2Vec2ForSequenceClassification, Wav2Vec2Processor import torchaudio # Load model and processor model = Wav2Vec2ForSequenceClassification.from_pretrained("Mrkomiljon/voiceGUARD") processor = Wav2Vec2Processor.from_pretrained("Mrkomiljon/voiceGUARD") # Inference function def classify_audio(audio_path, target_sample_rate=16000): # Load and preprocess audio waveform, sample_rate = torchaudio.load(audio_path) if sample_rate != target_sample_rate: resampler = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=target_sample_rate) waveform = resampler(waveform) # Ensure audio is 10 seconds (truncate/pad) max_length = target_sample_rate * 10 if waveform.size(1) > max_length: waveform = waveform[:, :max_length] elif waveform.size(1) < max_length: waveform = torch.nn.functional.pad(waveform, (0, max_length - waveform.size(1))) # Process input inputs = processor(waveform.squ…d331afd -
ADD model files
unknowna7a281c -
initial commit
Verified signature4c9d6ca