Update app.py

app.py

@@ -1,13 +1,30 @@
 import gradio as gr
-# Load model directly
-from transformers import AutoTokenizer, AutoModelForCausalLM
-# Use a pipeline as a high-level helper
-from transformers import pipeline
+from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
+from datasets import load_dataset
+import soundfile as sf
+import torch
 
-pipe = pipeline("text-generation", model="meta-llama/Llama-2-7b-chat-hf")
+# load model and tokenizer
+processor = Wav2Vec2Processor.from_pretrained("nguyenvulebinh/wav2vec2-base-vietnamese-250h")
+model = Wav2Vec2ForCTC.from_pretrained("nguyenvulebinh/wav2vec2-base-vietnamese-250h")
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+# define function to read in sound file
+def map_to_array(batch):
+    speech, _ = sf.read(batch["file"])
+    batch["speech"] = speech
+    return batch
 
+# tokenize
 
-gr.load("models/meta-llama/Llama-2-7b-hf").launch()
+def recognize_speech(audio):
+    ds = map_to_array({
+        "file": audio
+    })
+    input_values = processor(ds["speech"], return_tensors="pt", padding="longest").input_values  # Batch size 1
+    logits = model(input_values).logits
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = processor.batch_decode(predicted_ids)
+    return transcription[0]
+
+# launch a simple UI
+gr.Interface(fn=recognize_speech, inputs="microphone", outputs="text").launch()