init

.gitignore

@@ -0,0 +1,3 @@
+__pycache__/*
+.DS_Store
+.vscode/*%

README.md

@@ -9,4 +9,4 @@ app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## XLSR Wav2Vec2 real time  ASR demo in Tamil

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import pipeline
+import time
+
+# p = pipeline("automatic-speech-recognition", model="/Users/mkesavan/aidev/speechAI-trials/xlsr-wave2vec/wav2vec2-large-xls-r-300m-tamil-colab/checkpoint-1600")
+
+p = pipeline("automatic-speech-recognition", model="kmknair/wav2vec2-xlsr-tamil")
+
+def transcribe(audio, state=""):
+    time.sleep(2)
+    text = p(audio)["text"]
+    state += text + " " 
+    return state, state
+
+
+gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.Audio(source="microphone", type="filepath", streaming=True),
+        "state"
+    ],
+    outputs=[
+    "textbox",
+    "state"
+    ],
+    live=True).launch()

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,2 @@
+torch
+transformers