Update app.py

app.py

@@ -0,0 +1,55 @@
+import os
+os.system('git clone https://github.com/Open-Speech-EkStep/vakyansh-tts')
+os.chdir('vakyansh-tts') 
+os.system('bash install.sh')
+os.system('python setup.py bdist_wheel')
+os.system('pip install -e .')
+os.chdir('tts_infer')
+os.system('mkdir translit_models')
+os.chdir('translit_models')
+os.system('wget https://storage.googleapis.com/vakyaansh-open-models/translit_models/default_lineup.json')
+os.system('mkdir hindi')
+os.chdir('hindi')
+os.system('wget https://storage.googleapis.com/vakyaansh-open-models/translit_models/hindi/hindi_transliteration.zip')
+os.system('unzip hindi_transliteration')
+
+os.system('wget https://storage.googleapis.com/vakyansh-open-models/tts/hindi/hi-IN/female_voice_0/glow.zip')
+os.system('unzip glow.zip')
+
+os.system('wget https://storage.googleapis.com/vakyansh-open-models/tts/hindi/hi-IN/female_voice_0/hifi.zip')
+os.system('unzip hifi.zip')
+
+os.system('rm glow.zip')
+os.system('rm hifi.zip')
+
+os.chdir('/content/vakyansh-tts/')
+
+from tts_infer.tts import TextToMel, MelToWav
+from tts_infer.transliterate import XlitEngine
+from tts_infer.num_to_word_on_sent import normalize_nums
+
+import re
+from scipy.io.wavfile import write
+device = 'cpu'
+
+text_to_mel = TextToMel(glow_model_dir='/content/vakyansh-tts/tts_infer/translit_models/hindi/glow_ckp', device=device)
+mel_to_wav = MelToWav(hifi_model_dir='/content/vakyansh-tts/tts_infer/translit_models/hindi/hifi_ckp', device=device)
+
+def translit(text, lang):
+    reg = re.compile(r'[a-zA-Z]')
+    engine = XlitEngine(lang)
+    words = [engine.translit_word(word, topk=1)[lang][0] if reg.match(word) else word for word in text.split()]
+    updated_sent = ' '.join(words)
+    return updated_sent
+    
+def run_tts(text, lang):
+    text = text.replace('।', '.') # only for hindi models
+    text_num_to_word = normalize_nums(text, lang) # converting numbers to words in lang
+    text_num_to_word_and_transliterated = translit(text_num_to_word, lang) # transliterating english words to lang
+    
+    mel = text_to_mel.generate_mel(text_num_to_word_and_transliterated)
+    audio, sr = mel_to_wav.generate_wav(mel)
+    write(filename='temp.wav', rate=sr, data=audio) # for saving wav file, if needed
+    return (sr, audio)
+    
+_, audio = run_tts('hello my name is harveen', 'hi')