get rid of fairseq requirement

app.py

@@ -19,7 +19,6 @@ from subprocess import Popen
 import faiss
 from random import shuffle
 import json, datetime, requests
-from gtts import gTTS
 now_dir = os.getcwd()
 sys.path.append(now_dir)
 tmp = os.path.join(now_dir, "TEMP")
@@ -1426,53 +1425,53 @@ def stoptraining(mim):
     )
 
 
-def elevenTTS(xiapi, text, id, lang):
-    if xiapi!= '' and id !='': 
-        choice = chosen_voice[id]
-        CHUNK_SIZE = 1024
-        url = f"https://api.elevenlabs.io/v1/text-to-speech/{choice}"
-        headers = {
-        "Accept": "audio/mpeg",
-        "Content-Type": "application/json",
-        "xi-api-key": xiapi
-        }
-        if lang == 'en':
-            data = {
-            "text": text,
-            "model_id": "eleven_monolingual_v1",
-            "voice_settings": {
-            "stability": 0.5,
-            "similarity_boost": 0.5
-            }
-            }
-        else:
-            data = {
-            "text": text,
-            "model_id": "eleven_multilingual_v1",
-            "voice_settings": {
-            "stability": 0.5,
-            "similarity_boost": 0.5
-            }
-            }
-
-        response = requests.post(url, json=data, headers=headers)
-        with open('./temp_eleven.mp3', 'wb') as f:
-          for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
-              if chunk:
-                  f.write(chunk)
-        aud_path = save_to_wav('./temp_eleven.mp3')
-        return aud_path, aud_path
-    else:
-        tts = gTTS(text, lang=lang)
-        tts.save('./temp_gTTS.mp3')
-        aud_path = save_to_wav('./temp_gTTS.mp3')
-        return aud_path, aud_path
-
-def ilariaTTS(text, ttsvoice):
-    vo=language_dict[ttsvoice]
-    asyncio.run(edge_tts.Communicate(text, vo).save("./temp_ilaria.mp3"))
-    aud_path = save_to_wav('./temp_ilaria.mp3')
-    return aud_path, aud_path
+# def elevenTTS(xiapi, text, id, lang):
+#     if xiapi!= '' and id !='': 
+#         choice = chosen_voice[id]
+#         CHUNK_SIZE = 1024
+#         url = f"https://api.elevenlabs.io/v1/text-to-speech/{choice}"
+#         headers = {
+#         "Accept": "audio/mpeg",
+#         "Content-Type": "application/json",
+#         "xi-api-key": xiapi
+#         }
+#         if lang == 'en':
+#             data = {
+#             "text": text,
+#             "model_id": "eleven_monolingual_v1",
+#             "voice_settings": {
+#             "stability": 0.5,
+#             "similarity_boost": 0.5
+#             }
+#             }
+#         else:
+#             data = {
+#             "text": text,
+#             "model_id": "eleven_multilingual_v1",
+#             "voice_settings": {
+#             "stability": 0.5,
+#             "similarity_boost": 0.5
+#             }
+#             }
+
+#         response = requests.post(url, json=data, headers=headers)
+#         with open('./temp_eleven.mp3', 'wb') as f:
+#           for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
+#               if chunk:
+#                   f.write(chunk)
+#         aud_path = save_to_wav('./temp_eleven.mp3')
+#         return aud_path, aud_path
+#     else:
+#         tts = gTTS(text, lang=lang)
+#         tts.save('./temp_gTTS.mp3')
+#         aud_path = save_to_wav('./temp_gTTS.mp3')
+#         return aud_path, aud_path
+
+# def ilariaTTS(text, ttsvoice):
+#     vo=language_dict[ttsvoice]
+#     asyncio.run(edge_tts.Communicate(text, vo).save("./temp_ilaria.mp3"))
+#     aud_path = save_to_wav('./temp_ilaria.mp3')
+#     return aud_path, aud_path
 
 def transcribe_btn_click(audio_choice):
     batch_size = 1  # Adjust based on your GPU memory availability

requirements.txt

@@ -1,6 +1,3 @@
-gTTS
-elevenlabs
-edge-tts
 stftpitchshift==1.5.1
 torchcrepe
 setuptools
@@ -8,7 +5,6 @@ wheel
 whisper
 httpx==0.23.0
 faiss-gpu
-fairseq==0.12.2
 gradio==3.34.0
 ffmpeg-python
 praat-parselmouth