app

app.py

@@ -0,0 +1,27 @@
+from transformers import pipeline
+import gradio as gr
+import time
+
+asr = pipeline("automatic-speech-recognition", "../models/20220513-212939/_lm", device=0)
+# asr = pipeline("automatic-speech-recognition", "YSU/aspram")
+
+def transcribe(audio, state=""):
+    time.sleep(5)
+    text = asr(audio)["text"]
+    state += text + " "
+    print('chunk!')
+    return state, state
+
+gr.Interface(
+    fn=transcribe, 
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath"), 
+        "state"
+    ],
+    outputs=[
+        "textbox",
+        "state"
+    ],
+    live=True,
+    css='body {background-color: rgba(240, 200, 192)}',
+).launch()

packages.txt

@@ -0,0 +1,2 @@
+ffmpeg
+libsndfile1

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers
+librosa
+pyctcdecode
+pypi-kenlm