boumehdi

app.py

@@ -1,7 +1,25 @@
-import gradio as gr
+import librosa
+import torch
+from transformers import Wav2Vec2CTCTokenizer, Wav2Vec2ForCTC, Wav2Vec2Processor, TrainingArguments, Wav2Vec2FeatureExtractor, Trainer
 
-def greet(name):
-    return "Hello " + name + "!!"
+tokenizer = Wav2Vec2CTCTokenizer("./vocab.json", unk_token="[UNK]", pad_token="[PAD]", word_delimiter_token="|")
+processor = Wav2Vec2Processor.from_pretrained('boumehdi/wav2vec2-large-xlsr-moroccan-darija', tokenizer=tokenizer)
+model=Wav2Vec2ForCTC.from_pretrained('boumehdi/wav2vec2-large-xlsr-moroccan-darija')
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch(share=True)
+
+# load the audio data (use your own wav file here!)
+input_audio, sr = librosa.load('file.wav', sr=16000)
+
+# tokenize
+input_values = processor(input_audio, return_tensors="pt", padding=True).input_values
+
+# retrieve logits
+logits = model(input_values).logits
+
+tokens = torch.argmax(logits, axis=-1)
+
+# decode using n-gram
+transcription = tokenizer.batch_decode(tokens)
+
+# print the output
+print(transcription)