Update app.py

app.py

@@ -2,11 +2,34 @@ import gradio as gr
 
 #Get models
 #ASR model for input speech
-speech2text = gr.Interface.load("huggingface/facebook/hubert-large-ls960-ft",
-                                inputs=gr.inputs.Audio(label="Record Audio File", type="file", source = "microphone"))
-                                        
+import torch
+from transformers import Wav2Vec2Processor, HubertForCTC
+from datasets import load_dataset
+import soundfile as sf
+
+processor = Wav2Vec2Processor.from_pretrained("facebook/hubert-large-ls960-ft")
+model = HubertForCTC.from_pretrained("facebook/hubert-large-ls960-ft")
+
+def map_to_array(batch):
+    speech, _ = sf.read(batch["file"])
+    batch["speech"] = speech
+    return batch
+    
+ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
+ds = ds.map(map_to_array)
+
+input_values = processor(ds["speech"][0], return_tensors="pt").input_values  # Batch size 1
+logits = model(input_values).logits
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.decode(predicted_ids[0])
+
+#speech2text = gr.Interface.load("huggingface/facebook/hubert-large-ls960-ft",
+ #                               inputs=gr.inputs.Audio(label="Record Audio File", type="file", source = "microphone"))
+speech2text = gr.Interface.(transcription,
+                            inputs=gr.inputs.Audio(label="Record Audio File", type="file", source = "microphone"))                                        
 #translates english to spanish text                      
 translator = gr.Interface.load("huggingface/Helsinki-NLP/opus-mt-en-es",
+                                input=transcription
                                 outputs=gr.outputs.Textbox(label="English to Spanish Translated Text"))
 #TTS model for output speech                                
 text2speech = gr.Interface.load("huggingface/facebook/tts_transformer-es-css10",