n

README.md

@@ -1,5 +1,5 @@
 ---
-title: Speech analysis
+title: affective TTS
 emoji: 💤
 colorFrom: gray
 colorTo: gray

app.py

@@ -48,20 +48,23 @@ def audionar_tts(text=None,
         }
 
     if text is None or text.strip() == '':
-        text = 'No Audio or Txt Input'
+        text = 'No Txt Has been typed'
 
 
 
+    fs = 16000
 
     if lang not in language_names:  # StyleTTS2
         
+        fs = 24000
+        
         text = only_greek_or_only_latin(text, lang='eng')
 
         x = _tts.inference(text,
                            ref_s='wav/' + lang + '.wav')[0, 0, :].numpy()  # 24 Khz
     
     else:  # VITS
-        
+
         lang_code = lang_map.get(lang.lower(), lang.lower().split()[0].strip())
 
         global cached_lang_code, cached_net_g, cached_tokenizer
@@ -100,7 +103,7 @@ def audionar_tts(text=None,
 
 
     wavfile = '_vits_.wav'
-    audiofile.write(wavfile, x, 16000)    
+    audiofile.write(wavfile, x, fs)    
     return wavfile  # 2x file for [audio out & state to pass to the Emotion reco tAB]
 
 
@@ -140,9 +143,9 @@ VOICES = ['jv_ID_google-gmu_04982.wav',
         'en_US_vctk_p233.wav', 
         'it_IT_mls_4975.wav', 
         'en_US_vctk_p236.wav', 
-        'bn_multi_01232.wav', 
+        # 'bn_multi_01232.wav', 
         'bn_multi_5958.wav', 
-        'it_IT_mls_9185.wav', 
+        # 'it_IT_mls_9185.wav', 
         'en_US_vctk_p248.wav', 
         'en_US_vctk_p287.wav', 
         'it_IT_mls_9772.wav', 
@@ -199,8 +202,8 @@ VOICES = ['jv_ID_google-gmu_04982.wav',
         'en_US_vctk_p302.wav', 
         'jv_ID_google-gmu_08178.wav', 
         'en_US_vctk_p313.wav', 
-        'af_ZA_google-nwu_2418.wav', 
-        'bn_multi_00737.wav', 
+        # 'af_ZA_google-nwu_2418.wav', 
+        # 'bn_multi_00737.wav', 
         'en_US_vctk_p275.wav', # y
         'af_ZA_google-nwu_0184.wav', 
         'jv_ID_google-gmu_07638.wav', 
@@ -292,7 +295,7 @@ VOICES = ['jv_ID_google-gmu_04982.wav',
         'nl_nathalie.wav', 
         'it_IT_mls_8207.wav', 
         'ko_KO_kss.wav', 
-        'af_ZA_google-nwu_6590.wav', 
+        # 'af_ZA_google-nwu_6590.wav', 
         'jv_ID_google-gmu_00264.wav', 
         'tn_ZA_google-nwu_6234.wav', 
         'jv_ID_google-gmu_05522.wav', 
@@ -354,10 +357,10 @@ VOICES = ['jv_ID_google-gmu_04982.wav',
         'it_IT_mls_7936.wav', 
         'en_US_vctk_p301.wav', 
         'tn_ZA_google-nwu_0045.wav', 
-        'it_IT_mls_659.wav', 
+        # 'it_IT_mls_659.wav', 
         'tn_ZA_google-nwu_7674.wav', 
-        'it_IT_mls_12804.wav', 
-        'el_GR_rapunzelina.wav', 
+        # 'it_IT_mls_12804.wav', 
+        # 'el_GR_rapunzelina.wav', 
         'en_US_hifi-tts_6097.wav', 
         'en_US_vctk_p257.wav', 
         'jv_ID_google-gmu_07875.wav', 
@@ -381,7 +384,7 @@ VOICES = ['jv_ID_google-gmu_04982.wav',
         'de_DE_m-ailabs_karlsson.wav', 
         'en_US_cmu_arctic_awb.wav', 
         'en_US_vctk_p246.wav', 
-        'en_US_cmu_arctic_clb.wav', 
+        # 'en_US_cmu_arctic_clb.wav', 
         'en_US_vctk_p364.wav', 
         'nl_flemishguy.wav', 
         'en_US_vctk_p276.wav', # y
@@ -425,7 +428,7 @@ VOICES = ['jv_ID_google-gmu_04982.wav',
         # 'male-27-sad.wav', 
         'tn_ZA_google-nwu_1498.wav', 
         'fi_FI_harri-tapani-ylilammi.wav', 
-        'bn_multi_rm.wav', 
+        # 'bn_multi_rm.wav', 
         'ne_NP_ne-google_2139.wav', 
         'pl_PL_m-ailabs_piotr_nater.wav', 
         'fr_FR_siwis.wav',