Gabriel commited on
Commit
6a5ac94
1 Parent(s): 451f882
helper/text/help/faq_discussion/faq.md CHANGED
@@ -4,10 +4,10 @@
4
  **A**: Absolutely. Uploaded files are not saved or stored.
5
 
6
  **Q**: <u>Why am I always in a queue?</u>
7
- **A**: This is due to hardware constraints and rate limits imposed by Hugging Face. For alternative ways to use the app, refer to the **Documentation** tab under **Duplication for Own Use & API**.
8
 
9
- **Q**: <u>Why is inference slow?</u>
10
- **A**: The current speed is due to hardware limitations and the present state of the code. However, we plan to update the application in future releases, which will significantly improve inference times.
11
 
12
- **Q**: <u>Is batch inference possible?</u>
13
  **A**: Not currently, but we plan to add this feature in the future.
 
4
  **A**: Absolutely. Uploaded files are not saved or stored.
5
 
6
  **Q**: <u>Why am I always in a queue?</u>
7
+ **A**: This is due to hardware constraints and rate limits imposed by Hugging Face. For alternative ways to use the app, refer to the tab > **Documentation** under > **Duplication for Own Use & API**.
8
 
9
+ **Q**: <u>Why is Fast track so slow?</u>
10
+ **A**: The current speed is due to hardware limitations and the present state of the code. However, we plan to update the application in future releases, which will significantly improve run time and performance of the application.
11
 
12
+ **Q**: <u>Is possible to run Fast track or the API on multiple images on same time?</u>
13
  **A**: Not currently, but we plan to add this feature in the future.
helper/text/text_app.py CHANGED
@@ -6,7 +6,7 @@ class TextApp:
6
 
7
  <h1><center> HTRFLOW </center></h1>
8
 
9
- <p><center>Explore AI models for historical HTR developed by the Swedish National Archives </center></p>"""
10
 
11
  title_markdown_img = """
12
  <a href="https://riksarkivet.se">
 
6
 
7
  <h1><center> HTRFLOW </center></h1>
8
 
9
+ <p><center>Explore AI models for Handwritten Text Recogntion developed by the Swedish National Archives </center></p>"""
10
 
11
  title_markdown_img = """
12
  <a href="https://riksarkivet.se">
tabs/htr_tool.py CHANGED
@@ -58,7 +58,7 @@ with gr.Blocks() as htr_tool_tab:
58
  )
59
 
60
  selection_text_from_image_viewer = gr.Textbox(
61
- interactive=False, label="Text Selector", info="Select a mask on Image Viewer to return text"
62
  )
63
 
64
  with gr.Tab("Compare") as tab_model_compare_selector:
 
58
  )
59
 
60
  selection_text_from_image_viewer = gr.Textbox(
61
+ interactive=False, label="Text Selector", info="Select a line on Image Viewer to return text"
62
  )
63
 
64
  with gr.Tab("Compare") as tab_model_compare_selector:
tabs/stepwise_htr_tool.py CHANGED
@@ -197,7 +197,7 @@ with gr.Blocks() as stepwise_htr_tool_tab:
197
  )
198
 
199
  with gr.Row():
200
- copy_textarea = gr.Button("Copy Text", variant="secondary", visible=True, scale=1)
201
 
202
  transcribe_button = gr.Button("Run", variant="primary", visible=True, scale=1)
203
 
@@ -259,14 +259,14 @@ with gr.Blocks() as stepwise_htr_tool_tab:
259
  )
260
 
261
  with gr.Row(equal_height=False):
262
- cer_output = gr.Textbox(label="CER:")
263
  gr.Markdown("")
264
  calc_cer_button = gr.Button("Calculate CER", variant="primary", visible=True)
265
 
266
  with gr.Column(scale=1, visible=True):
267
  mapping_dict = gr.Variable()
268
  transcribed_text_df_finish = gr.Dataframe(
269
- headers=["Transcribed text", "Pred score"],
270
  max_rows=14,
271
  col_count=(2, "fixed"),
272
  wrap=True,
 
197
  )
198
 
199
  with gr.Row():
200
+ copy_textarea = gr.Button("Copy text", variant="secondary", visible=True, scale=1)
201
 
202
  transcribe_button = gr.Button("Run", variant="primary", visible=True, scale=1)
203
 
 
259
  )
260
 
261
  with gr.Row(equal_height=False):
262
+ cer_output = gr.Textbox(label="Character Error Rate")
263
  gr.Markdown("")
264
  calc_cer_button = gr.Button("Calculate CER", variant="primary", visible=True)
265
 
266
  with gr.Column(scale=1, visible=True):
267
  mapping_dict = gr.Variable()
268
  transcribed_text_df_finish = gr.Dataframe(
269
+ headers=["Transcribed text", "Prediction score"],
270
  max_rows=14,
271
  col_count=(2, "fixed"),
272
  wrap=True,