add more example test cases
Browse files- app.py +10 -14
- examples/mononeg.wav +3 -0
- examples/monopos.wav +3 -0
app.py
CHANGED
@@ -1,25 +1,15 @@
|
|
1 |
import gradio as gr
|
2 |
import requests
|
3 |
-
|
|
|
4 |
from sentiment_analysis import sentiment_analyser
|
5 |
from summary import summarizer
|
6 |
from topic import topic_gen
|
7 |
-
from data import data
|
8 |
-
|
9 |
-
def transcribe2():
|
10 |
-
response = requests.post("https://dwarkesh-whisper-speaker-recognition.hf.space/run/predict", json={
|
11 |
-
"data": [
|
12 |
-
{"name":"audio.wav","data":"data:audio/wav;base64,UklGRiQAAABXQVZFZm10IBAAAAABAAEARKwAAIhYAQACABAAZGF0YQAAAAA="},
|
13 |
-
2,
|
14 |
-
]}).json()
|
15 |
|
16 |
-
data = response["data"]
|
17 |
|
18 |
def main(audio_file, number_of_speakers):
|
19 |
# Audio to Text Converter
|
20 |
-
|
21 |
-
# print(text_data)
|
22 |
-
text_data = data
|
23 |
topic = topic_gen(text_data)[0]["generated_text"]
|
24 |
summary = summarizer(text_data)[0]["summary_text"]
|
25 |
sent_analy = sentiment_analyser(text_data)
|
@@ -28,7 +18,11 @@ def main(audio_file, number_of_speakers):
|
|
28 |
|
29 |
# UI Interface on the Hugging Face Page
|
30 |
with gr.Blocks() as demo:
|
31 |
-
gr.Markdown("
|
|
|
|
|
|
|
|
|
32 |
with gr.Box():
|
33 |
with gr.Row():
|
34 |
with gr.Column():
|
@@ -46,6 +40,8 @@ with gr.Blocks() as demo:
|
|
46 |
gr.Examples(
|
47 |
examples=[
|
48 |
["./examples/sample4.wav", 2],
|
|
|
|
|
49 |
],
|
50 |
inputs=[audio_file, number_of_speakers],
|
51 |
outputs=[topic, summary, sentiment_analysis],
|
|
|
1 |
import gradio as gr
|
2 |
import requests
|
3 |
+
|
4 |
+
from transcribe import transcribe
|
5 |
from sentiment_analysis import sentiment_analyser
|
6 |
from summary import summarizer
|
7 |
from topic import topic_gen
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
|
|
9 |
|
10 |
def main(audio_file, number_of_speakers):
|
11 |
# Audio to Text Converter
|
12 |
+
text_data = transcribe(audio_file, number_of_speakers)
|
|
|
|
|
13 |
topic = topic_gen(text_data)[0]["generated_text"]
|
14 |
summary = summarizer(text_data)[0]["summary_text"]
|
15 |
sent_analy = sentiment_analyser(text_data)
|
|
|
18 |
|
19 |
# UI Interface on the Hugging Face Page
|
20 |
with gr.Blocks() as demo:
|
21 |
+
gr.Markdown("""
|
22 |
+
# Shravan - Unlocking Value from Call Data
|
23 |
+
|
24 |
+
> **NOTE:** You need to give a `.wav` audio file and the audio file should be `monochannel`.
|
25 |
+
""")
|
26 |
with gr.Box():
|
27 |
with gr.Row():
|
28 |
with gr.Column():
|
|
|
40 |
gr.Examples(
|
41 |
examples=[
|
42 |
["./examples/sample4.wav", 2],
|
43 |
+
["./examples/monopos.wav", 2],
|
44 |
+
["./examples/mononeg.wav", 2],
|
45 |
],
|
46 |
inputs=[audio_file, number_of_speakers],
|
47 |
outputs=[topic, summary, sentiment_analysis],
|
examples/mononeg.wav
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48ff84445d6358625065758ff2911259481b66151c054b712e752a6aa02f2f21
|
3 |
+
size 2939982
|
examples/monopos.wav
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebd054310c0b00ea193bc2dba688a95abccb236fd477df51fd0fd277c15748cf
|
3 |
+
size 3787854
|