Update components/pexels.py

components/pexels.py

@@ -46,22 +46,35 @@ def download_video(data, parent_path, height, width, links, i):
                     print("Sucessfully saved video in", os.path.join(parent_path,str(i) + '_' + str(v['id'])) + '.mp4')
                     return x['id']
 
-def generate_voice(text, model, tokenizer):
+def generate_voice(text, model, tokenizer, model2, tokenizer2, text_cls):
     speeches = []
-    for x in text:
-        inputs = tokenizer(x, return_tensors="pt")
 
-    with torch.no_grad():
-        output = model(**inputs).waveform
-    speeches.append(output)
-    return speeches
+    
+    for x in text:
+        x = x+"."
+        if text_cls(x)[0]['label'][:4] == 'Indo':
+            inputs = tokenizer(x, return_tensors="pt")
+    
+            with torch.no_grad():
+                output = model(**inputs).waveform
+            speeches.append(output)
+            
+        else :
+            inputs = tokenizer2(x, return_tensors="pt")
+    
+            with torch.no_grad():
+                output = model2(**inputs).waveform
+            speeches.append(output)
+            
+    return speeches, [len(x)/16500 for x in speeches]
 
 # Utilizing the LLMs to find the relevant videos 
-def generate_videos(text, api_key, orientation, height, width, model, tokenizer):
+def generate_videos(text, api_key, orientation, height, width, model, tokenizer, model2, tokenizer2, text_cls):
     links = []
     try :
         # Split the paragraph by sentences
         sentences = list(filter(None,[x.strip() for x in re.split(r'[^A-Za-z0-9 -]', text)]))
+        # print(len(sentences))
         
         # Create directory with the name
         di = str(datetime.datetime.now())
@@ -77,8 +90,9 @@ def generate_videos(text, api_key, orientation, height, width, model, tokenizer)
             data = search_pexels(s, api_key, orientation.lower())
             link = download_video(data, di, height, width, links,i)
             links.append(link)
+
         
-        speeches = generate_voice(sentences, model, tokenizer)
+        speeches, length_speech = generate_voice(sentences, model, tokenizer, model2, tokenizer2, text_cls)
 
         sf.write("x.wav", torch.cat(speeches, 1)[0], 16500)
             
@@ -87,5 +101,5 @@ def generate_videos(text, api_key, orientation, height, width, model, tokenizer)
         print("Error! Failed generating videos")
         print(e)
     
-    return di, sentences
+    return di, sentences, length_speech