update words

app.py

@@ -59,9 +59,9 @@ from cosyvoice.cli.cosyvoice import CosyVoice2
 from cosyvoice.utils.file_utils import load_wav, logging
 from cosyvoice.utils.common import set_all_random_seed
 
-inference_mode_list = ['3s Speedy Convertion', 'Natural Language Control']
-instruct_dict = {'3s Speedy Convertion': '1. Upload prompt wav file (or record from mic), no longer than 30s, wav file will be used if provided at the same time\n2. Input prompt transcription\n3. click \'Speech Synthesis\' button',
-                 'Natural Language Control': '1. Upload prompt wav file (or record from mic), no longer than 30s, wav file will be used if provided at the same time\n2. Input instruct\n3. click \'Speech Synthesis\' button'}
+inference_mode_list = ['3s Voice Clone', 'Instructed Voice Generation']
+instruct_dict = {'3s Voice Clone': '1. Upload prompt wav file (or record from mic), no longer than 30s, wav file will be used if provided at the same time\n2. Input prompt transcription\n3. click \'Speech Synthesis\' button',
+                 'Instructed Voice Generation': '1. Upload prompt wav file (or record from mic), no longer than 30s, wav file will be used if provided at the same time\n2. Input instruct\n3. click \'Speech Synthesis\' button'}
 stream_mode_list = [('No', False), ('Yes', True)]
 max_val = 0.8
 
@@ -107,25 +107,25 @@ def generate_audio(tts_text, mode_checkbox_group, prompt_text, prompt_wav_upload
     else:
         prompt_wav = None
     # if instruct mode, please make sure that model is iic/CosyVoice-300M-Instruct and not cross_lingual mode
-    if mode_checkbox_group in ['Natural Language Control']:
+    if mode_checkbox_group in ['Instructed Voice Generation']:
         if instruct_text == '':
-            gr.Warning('You are using Natural Language Control mode, please input the instruct.')
+            gr.Warning('You are using Instructed Voice Generation mode, please input the instruct.')
             yield (target_sr, default_data)
         if prompt_wav is None:
-            gr.Info('You are using Natural Language Control mode, please upload the prompt audio.')
+            gr.Info('You are using Instructed Voice Generation mode, please upload the prompt audio.')
     # if cross_lingual mode, please make sure that model is iic/CosyVoice-300M and tts_text prompt_text are different language
-    if mode_checkbox_group in ['Cross-lingual Convertion']:
+    if mode_checkbox_group in ['Cross-lingual Clone']:
         if cosyvoice.frontend.instruct is True:
-            gr.Warning('You are using the cross-lingual Convertion mode. The {} model does not support this mode. Please use the iic/CosyVoice-300M model.'.format(args.model_dir))
+            gr.Warning('You are using the cross-lingual Clone mode. The {} model does not support this mode. Please use the iic/CosyVoice-300M model.'.format(args.model_dir))
             yield (target_sr, default_data)
         if instruct_text != '':
-            gr.Info('You are using the cross-lingual Convertion mode. The instruct text will be ignored.')
+            gr.Info('You are using the cross-lingual Clone mode. The instruct text will be ignored.')
         if prompt_wav is None:
-            gr.Warning('You are using the cross-lingual Convertion mode. Please provide the prompt audio.')
+            gr.Warning('You are using the cross-lingual Clone mode. Please provide the prompt audio.')
             yield (target_sr, default_data)
-        gr.Info('You are using the cross-lingual Convertion mode. Please ensure that the synthesis text and prompt text are in different languages.')
+        gr.Info('You are using the cross-lingual Clone mode. Please ensure that the synthesis text and prompt text are in different languages.')
     # if in zero_shot cross_lingual, please make sure that prompt_text and prompt_wav meets requirements
-    if mode_checkbox_group in ['3s Speedy Convertion', 'Cross-lingual Convertion']:
+    if mode_checkbox_group in ['3s Voice Clone', 'Cross-lingual Clone']:
         if prompt_wav is None:
             gr.Warning('Empty prompt found, please check the prompt text.')
             yield (target_sr, default_data)
@@ -137,12 +137,12 @@ def generate_audio(tts_text, mode_checkbox_group, prompt_text, prompt_wav_upload
         if instruct_text != '' or prompt_wav is not None or prompt_text != '':
             gr.Info('You are using Pretrained Voice mode. Pretrained Voice/Instruct will be ingnored.')
     # zero_shot mode only use prompt_wav prompt text
-    if mode_checkbox_group in ['3s Speedy Convertion']:
+    if mode_checkbox_group in ['3s Voice Clone']:
         if prompt_text == '':
             gr.Warning('Empty prompt found, please check the prompt text.')
             yield (target_sr, default_data)
         if instruct_text != '':
-            gr.Info('You are using 3s Speedy Convertion mode. Pretrained Voice/Instruct will be ingnored.')
+            gr.Info('You are using 3s Voice Clone mode. Pretrained Voice/Instruct will be ingnored.')
         info = torchaudio.info(prompt_wav)
         if info.num_frames / info.sample_rate > 10:
             gr.Warning('Please use prompt audio shorter than 10s.')
@@ -153,13 +153,13 @@ def generate_audio(tts_text, mode_checkbox_group, prompt_text, prompt_wav_upload
         set_all_random_seed(seed)
         for i in cosyvoice.inference_sft(tts_text, sft_dropdown, stream=stream, speed=speed):
             yield (target_sr, i['tts_speech'].numpy().flatten())
-    elif mode_checkbox_group == '3s Speedy Convertion':
+    elif mode_checkbox_group == '3s Voice Clone':
         logging.info('get zero_shot inference request')
         prompt_speech_16k = postprocess(load_wav(prompt_wav, prompt_sr))
         set_all_random_seed(seed)
         for i in cosyvoice.inference_zero_shot(tts_text, prompt_text, prompt_speech_16k, stream=stream, speed=speed):
             yield (target_sr, i['tts_speech'].numpy().flatten())
-    elif mode_checkbox_group == 'Cross-lingual Convertion':
+    elif mode_checkbox_group == 'Cross-lingual Clone':
         logging.info('get cross_lingual inference request')
         prompt_speech_16k = postprocess(load_wav(prompt_wav, prompt_sr))
         set_all_random_seed(seed)