example

.gitignore

@@ -0,0 +1 @@
+venv

README.md

@@ -1,7 +1,7 @@
 ---
-title: Testing
-emoji: 💩
-colorFrom: blue
+title: Speech Recognition Example
+emoji: 🗣
+colorFrom: red
 colorTo: pink
 sdk: gradio
 sdk_version: 2.9.4

app.py

@@ -4,8 +4,20 @@ from transformers import pipeline
 
 model = pipeline(task="automatic-speech-recognition",
                  model="facebook/s2t-medium-librispeech-asr")
-gr.Interface.from_pipeline(model,
-                           title="Automatic Speech Recognition (ASR)",
-                           description="Using pipeline with Facebook S2T for ASR.",
-                           examples=['ljspeech.wav',]
-                           ).launch()
+
+
+def predict_speech_to_text(audio):
+    prediction = model(audio)
+    text = prediction['text']
+    return text
+
+
+gr.Interface(fn=predict_speech_to_text,
+             title="Automatic Speech Recognition (ASR)",
+             inputs=gr.inputs.Audio(
+                 source="microphone", type="filepath", label="Input"),
+             outputs=gr.outputs.Textbox(label="Output"),
+             description="Using pipeline with Facebook S2T for ASR.",
+             examples=['ljspeech.wav'],
+             allow_flagging='never'
+             ).launch()

requirements.txt

@@ -2,3 +2,4 @@ torch
 torchaudio
 transformers
 sentencepiece
+gradio