rutsam commited on
Commit
b80b9f8
1 Parent(s): 9bb48e9

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -5
app.py CHANGED
@@ -27,7 +27,7 @@ def asr_transcript(audio):
27
  data={}
28
  if audio:
29
  text_asr = asr_model.transcribe_file(audio.name)
30
- text_nemo_trasducer = transcribe(audio, "stt_rw_conformer_ctc_large")
31
  with open(audio.name,'rb') as f:
32
  audio_proper = f.read()
33
  stt_engine = SpeechToTextEngine()
@@ -39,8 +39,7 @@ def asr_transcript(audio):
39
  # Running the transcription
40
  text_coqui = stt_engine.run(audio_proper)
41
 
42
- return text_asr.lower() , text_coqui , text_nemo_trasducer
43
- else:
44
  return "File not valid"
45
 
46
  gradio_ui = gr.Interface(
@@ -52,8 +51,7 @@ gradio_ui = gr.Interface(
52
  """,
53
  inputs=[ gr.inputs.Audio(label="Upload Audio File", type="file", optional=False)],
54
  outputs=[gr.outputs.Textbox(label="Recognized speech from speechbrain model"),
55
- gr.outputs.Textbox(label="Recognized speech from coqui STT model"),
56
- gr.outputs.Textbox(label="Recognized speech from NVIDIA conformer ctc large model")]
57
  # examples = [["sample_1.wav"],["sample_2.wav"]]
58
  )
59
 
 
27
  data={}
28
  if audio:
29
  text_asr = asr_model.transcribe_file(audio.name)
30
+ #text_nemo_trasducer = transcribe(audio, "stt_rw_conformer_ctc_large")
31
  with open(audio.name,'rb') as f:
32
  audio_proper = f.read()
33
  stt_engine = SpeechToTextEngine()
 
39
  # Running the transcription
40
  text_coqui = stt_engine.run(audio_proper)
41
 
42
+ return text_asr.lower() , text_coqui
 
43
  return "File not valid"
44
 
45
  gradio_ui = gr.Interface(
 
51
  """,
52
  inputs=[ gr.inputs.Audio(label="Upload Audio File", type="file", optional=False)],
53
  outputs=[gr.outputs.Textbox(label="Recognized speech from speechbrain model"),
54
+ gr.outputs.Textbox(label="Recognized speech from coqui STT model")]
 
55
  # examples = [["sample_1.wav"],["sample_2.wav"]]
56
  )
57