1

app.py

@@ -2,10 +2,12 @@ import gradio as gr
 import ffmpeg
 from pathlib import Path
 import os
+import ast
 import json
 import base64
 import requests
-import ast
+
+
 
 API_URL = "https://api-inference.huggingface.co/models/facebook/wav2vec2-base-960h"
 #headers = {"Authorization": "Bearer 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"}
@@ -26,6 +28,7 @@ def generate_transcripts(in_video): #generate_gifs(in_video, gif_transcript):
     model_response = query_api(audio_memory)
     
     #model response has both - transcripts as well as character timestamps or chunks
+    print(f"model_response is : {model_response}")
     transcription = model_response["text"].lower()
     chnk = model_response["chunks"]
     
@@ -77,6 +80,7 @@ def query_api(audio_bytes: bytes):
     """
     Query for Huggingface Inference API for Automatic Speech Recognition task
     """
+    print("********* Inside query_api() **********")
     payload = json.dumps({
         "inputs": base64.b64encode(audio_bytes).decode("utf-8"),
         "parameters": {
@@ -90,6 +94,7 @@ def query_api(audio_bytes: bytes):
     response = requests.request(
         "POST", API_URL, headers=headers, data=payload)
     json_reponse = json.loads(response.content.decode("utf-8"))
+    print(f"json_reponse is :{json_reponse}")
     return json_reponse