Upload folder using huggingface_hub
Browse files
README.md
CHANGED
@@ -1,12 +1,9 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji: 🐢
|
4 |
-
colorFrom: gray
|
5 |
-
colorTo: green
|
6 |
-
sdk: gradio
|
7 |
-
sdk_version: 4.41.0
|
8 |
app_file: app.py
|
9 |
-
|
|
|
10 |
---
|
11 |
|
12 |
-
|
|
|
|
1 |
---
|
2 |
+
title: Suanfamama_Speech_Recognition_Synthesis
|
|
|
|
|
|
|
|
|
|
|
3 |
app_file: app.py
|
4 |
+
sdk: gradio
|
5 |
+
sdk_version: 4.29.0
|
6 |
---
|
7 |
|
8 |
+
## Reference
|
9 |
+
1. Real Time Speech Recognition https://www.gradio.app/guides/real-time-speech-recognition
|
app.py
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import pipeline
|
3 |
+
import numpy as np
|
4 |
+
|
5 |
+
transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
|
6 |
+
|
7 |
+
def transcribe(audio):
|
8 |
+
sr, y = audio
|
9 |
+
y = y.astype(np.float32)
|
10 |
+
y /= np.max(np.abs(y))
|
11 |
+
|
12 |
+
return transcriber({"sampling_rate": sr, "raw": y})["text"]
|
13 |
+
|
14 |
+
demo = gr.Interface(
|
15 |
+
transcribe,
|
16 |
+
gr.Audio(sources=["microphone"]),
|
17 |
+
"text",
|
18 |
+
)
|
19 |
+
|
20 |
+
demo.launch()
|