Update app.py

app.py

@@ -81,16 +81,17 @@ def generate_image(api_key, text):
 ####
 
 ####
+
 import torch
 from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
-import soundfile as sf
 
-# Load the pretrained English model and processor
-model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-medium-libri-lighten")
-processor = Speech2TextProcessor.from_pretrained("facebook/s2t-medium-libri-lighten")
+
+# Load the pretrained model and processor
+model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
+processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
 
 # Load your local audio file
-#audio_input, sampling_rate = sf.read("path/to/your/local/audio/file.wav")
+audio_input, sampling_rate = sf.read("/content/1001_IEO_DIS_HI.wav")
 
 # Convert the audio to PyTorch tensors using the processor
 inputs = processor(audio_input, sampling_rate=sampling_rate, return_tensors="pt")
@@ -104,8 +105,8 @@ generated_ids = model.generate(
 
 # Decode the generated transcription
 transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)
-print(transcription)
-####
+
+###