spriambada3 commited on
Commit
2ce0a69
·
1 Parent(s): aaf2b16

add dataset

Browse files
Files changed (3) hide show
  1. README.md +3 -3
  2. app.py +38 -2
  3. requirements.txt +3 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- title: SOAP AI
3
  emoji: 👀
4
- colorFrom: red
5
- colorTo: gray
6
  sdk: gradio
7
  sdk_version: 5.17.0
8
  app_file: app.py
 
1
  ---
2
+ title: eHealth Transcribe
3
  emoji: 👀
4
+ colorFrom: white
5
+ colorTo: blue
6
  sdk: gradio
7
  sdk_version: 5.17.0
8
  app_file: app.py
app.py CHANGED
@@ -5,6 +5,39 @@ import gradio as gr
5
  from google import genai
6
  from google.genai import types
7
  import asyncio
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
 
9
 
10
  def audio_from_bytes(audio_file_path: str):
@@ -103,7 +136,9 @@ def save_user_data(username, email):
103
 
104
  with open(DATA_FILE, "w") as file:
105
  json.dump(data, file, indent=4)
106
-
 
 
107
  return data
108
 
109
 
@@ -194,11 +229,12 @@ with gr.Blocks() as demo:
194
  user_block = gr.Column(visible=False)
195
  with user_block:
196
  counter_display = gr.Textbox(label="Status Message", interactive=False)
 
197
  gr.Interface(
198
  fn=transcribe_and_summarize,
199
  inputs=[gr.Audio(type="filepath", sources="microphone"), session],
200
  outputs=["text", counter_display, session],
201
- description="pastikan HP/Laptop memiliki microphone untuk merekam percakapan dokter-pasien menjadi rekam medis SOAP. Akun berlangganan https://ehealth.co.id dapat terintegrasi SATUSEHAT & BPJS secara otomatis",
202
  allow_flagging="never",
203
  )
204
  use_case_description = gr.Markdown(
 
5
  from google import genai
6
  from google.genai import types
7
  import asyncio
8
+ from datasets import load_dataset, DatasetDict, Dataset
9
+ from huggingface_hub import login
10
+ import datetime
11
+
12
+ # Authenticate with HF token
13
+ hf_token = os.getenv("HF_TOKEN")
14
+ login(token=hf_token)
15
+ dataset_name = "spriambada3/ehealth_transcribe"
16
+
17
+
18
+ def init_dataset():
19
+ try:
20
+ dataset = load_dataset(dataset_name)
21
+ except Exception as e:
22
+ print(e)
23
+ dataset = DatasetDict(
24
+ {"data": Dataset.from_dict({"logintime": [], "email": [], "wa": []})}
25
+ )
26
+ print("init dataset result ")
27
+ print(dataset)
28
+ return dataset
29
+
30
+
31
+ def add_user(dataset, email, wa):
32
+ new_data = {
33
+ "logintime": datetime.datetime.now(),
34
+ "email": email,
35
+ "wa": wa,
36
+ }
37
+ dataset["data"] = dataset["data"].add_item(new_data)
38
+ dataset.push_to_hub(dataset_name) # Save to HF Hub
39
+
40
+ print("add data successful")
41
 
42
 
43
  def audio_from_bytes(audio_file_path: str):
 
136
 
137
  with open(DATA_FILE, "w") as file:
138
  json.dump(data, file, indent=4)
139
+ wa = username
140
+ dataset = init_dataset()
141
+ add_user(dataset, email, wa)
142
  return data
143
 
144
 
 
229
  user_block = gr.Column(visible=False)
230
  with user_block:
231
  counter_display = gr.Textbox(label="Status Message", interactive=False)
232
+
233
  gr.Interface(
234
  fn=transcribe_and_summarize,
235
  inputs=[gr.Audio(type="filepath", sources="microphone"), session],
236
  outputs=["text", counter_display, session],
237
+ description="Halo, pastikan HP/Laptop memiliki microphone untuk merekam percakapan dokter-pasien menjadi rekam medis SOAP. Akun berlangganan https://ehealth.co.id dapat terintegrasi SATUSEHAT & BPJS secara otomatis",
238
  allow_flagging="never",
239
  )
240
  use_case_description = gr.Markdown(
requirements.txt CHANGED
@@ -1,3 +1,5 @@
1
  gradio==5.17.0
2
  python-dotenv==1.0.1
3
- google-genai
 
 
 
1
  gradio==5.17.0
2
  python-dotenv==1.0.1
3
+ google-genai
4
+ huggingface_hub
5
+ datasets