use text

app.py

@@ -4,6 +4,7 @@ import gradio as gr
 import numpy as np
 from TTS.api import TTS
 from huggingface_hub import snapshot_download
+import subprocess
 
 
 MAX_TXT_LEN = 100
@@ -24,13 +25,16 @@ def generate_audio(text):
     # )
     # if synthesizer is None:
     #     raise NameError("model not found")
-    tts = TTS(model_path="Kinyarwanda_YourTTS/model.pth",
-            config_path="Kinyarwanda_YourTTS/config.json",
-            tts_speakers_file="Kinyarwanda_YourTTS/speakers.pth",
-            encoder_checkpoint="Kinyarwanda_YourTTS/SE_checkpoint.pth.tar",
-            encoder_config="Kinyarwanda_YourTTS/config_se.json",)
-    wav = tts.tts(text, speaker_wav="kinyarwanda_YourTTS/conditioning_audio.wav")
-    return wav
+    # tts = TTS(model_path="Kinyarwanda_YourTTS/model.pth",
+    #         config_path="Kinyarwanda_YourTTS/config.json",
+    #         tts_speakers_file="Kinyarwanda_YourTTS/speakers.pth",
+    #         encoder_checkpoint="Kinyarwanda_YourTTS/SE_checkpoint.pth.tar",
+    #         encoder_config="Kinyarwanda_YourTTS/config_se.json",)
+    # wav = tts.tts(text, speaker_wav="kinyarwanda_YourTTS/conditioning_audio.wav")
+    # return wav
+    text1 = subprocess.check_output("ls", shell=True)+'   '+ subprocess.check_output("ls", shell=True)
+    text2 = text1.decode("utf-8")
+    return text2
     # with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
     #     synthesizer.save_wav(wav, fp)
     #     return fp.name
@@ -43,7 +47,8 @@ iface = gr.Interface(
             default="This sentence has been generated by a speech synthesis system.",
         ),
     ],
-    outputs=gr.outputs.Audio(type="numpy",label="Output"),
+    # outputs=gr.outputs.Audio(type="numpy",label="Output"),
+    outputs=gr.outputs.Textbox(label="Recognized speech from speechbrain model"),
     title="Kinyarwanda tts Demo",
     description="Kinyarwanda tts build with ",
     allow_flagging=False,