scribe-cli 0.7.6__tar.gz → 0.7.7__tar.gz

{scribe_cli-0.7.6/scribe_cli.egg-info → scribe_cli-0.7.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: scribe-cli
-Version: 0.7.6
+Version: 0.7.7
 Summary: scribe is a local speech recognition tool that provides real-time transcription using vosk and whisper AI, with the goal of serving as a virtual keyboard on a computer
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT License
@@ -44,6 +44,7 @@ Requires-Dist: sounddevice
 Requires-Dist: tqdm
 Requires-Dist: requests
 Requires-Dist: pyperclip
+Requires-Dist: unidecode
 Provides-Extra: keyboard
 Requires-Dist: pynput; extra == "keyboard"
 Provides-Extra: whisper
@@ -60,7 +61,7 @@ Requires-Dist: vosk; extra == "all"
 Requires-Dist: pystray; extra == "all"
 
 [![python](https://img.shields.io/badge/python-3.12-blue.svg)]()
-[![pypi](https://github.com/perrette/scribe/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/papers-cli)
+[![pypi](https://github.com/perrette/scribe/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/scribe-cli)
 
 # Scribe
 
@@ -83,7 +84,7 @@ sudo apt-get install portaudio19-dev xclip
 See additional requirements for the [icon tray](#system-tray-icon-experimental) and [keyboard](#virtual-keyboard-experimental) options. The python dependencies should be dealt with automatically:
 
 ```bash
-pip install scribe-cli[all]"
+pip install scribe-cli[all]
 ```
 
 (note the `-cli` suffix for client)
@@ -121,7 +122,7 @@ With the `whisker` model you need to stop the registration manually before the t
 there is a maximum duration after which it will stop by itself, which is setup to 60s by default (unless `--duration` is set to something else).
 
 The `vosk` backend is much faster and very good at doing real-time transcription for one language, but tended to make more mistakes in my tests and it does not do punctuation.
-Use mainly for longer typing session with the [keyboard](#virtual-keyboard-advanced) option, e.g. to make notes.
+It becomes really powerful when used for longer or interactive typing session with the [keyboard](#virtual-keyboard-experimental) option, e.g. to make notes or chat with an AI.
 There are many [vosk models](https://alphacephei.com/vosk/models) available, and here a few are associated to [a handful of languages](scribe/models.toml) `en`, `fr`, `it`, `de` (so far).
 
 To skip the initial selection menu you can do:

{scribe_cli-0.7.6 → scribe_cli-0.7.7}/README.md

@@ -1,5 +1,5 @@
 [![python](https://img.shields.io/badge/python-3.12-blue.svg)]()
-[![pypi](https://github.com/perrette/scribe/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/papers-cli)
+[![pypi](https://github.com/perrette/scribe/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/scribe-cli)
 
 # Scribe
 
@@ -22,7 +22,7 @@ sudo apt-get install portaudio19-dev xclip
 See additional requirements for the [icon tray](#system-tray-icon-experimental) and [keyboard](#virtual-keyboard-experimental) options. The python dependencies should be dealt with automatically:
 
 ```bash
-pip install scribe-cli[all]"
+pip install scribe-cli[all]
 ```
 
 (note the `-cli` suffix for client)
@@ -60,7 +60,7 @@ With the `whisker` model you need to stop the registration manually before the t
 there is a maximum duration after which it will stop by itself, which is setup to 60s by default (unless `--duration` is set to something else).
 
 The `vosk` backend is much faster and very good at doing real-time transcription for one language, but tended to make more mistakes in my tests and it does not do punctuation.
-Use mainly for longer typing session with the [keyboard](#virtual-keyboard-advanced) option, e.g. to make notes.
+It becomes really powerful when used for longer or interactive typing session with the [keyboard](#virtual-keyboard-experimental) option, e.g. to make notes or chat with an AI.
 There are many [vosk models](https://alphacephei.com/vosk/models) available, and here a few are associated to [a handful of languages](scribe/models.toml) `en`, `fr`, `it`, `de` (so far).
 
 To skip the initial selection menu you can do:
@@ -124,4 +124,4 @@ e.g.
 scribe-install --backend whisper --model small
 ```
 
-After that just typing Cmd + scri... at any time from any where will conveniently start the app in its own terminal with the prescribed options.
+After that just typing Cmd + scri... at any time from any where will conveniently start the app in its own terminal with the prescribed options.

{scribe_cli-0.7.6 → scribe_cli-0.7.7}/pyproject.toml

@@ -18,6 +18,7 @@ dependencies = [
     "tqdm",
     "requests",
     "pyperclip",
+    "unidecode",
 ]
 
 classifiers = [

{scribe_cli-0.7.6 → scribe_cli-0.7.7}/scribe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.7.6'
-__version_tuple__ = version_tuple = (0, 7, 6)
+__version__ = version = '0.7.7'
+__version_tuple__ = version_tuple = (0, 7, 7)

{scribe_cli-0.7.6 → scribe_cli-0.7.7}/scribe/app.py

@@ -151,6 +151,7 @@ def get_parser():
     parser.add_argument("--keyboard", action="store_true")
     parser.add_argument("--no-clipboard", dest="clipboard", action="store_false")
     parser.add_argument("--latency", default=0, type=float, help="keyboard latency")
+    parser.add_argument("--ascii", action="store_true", help="Use unidecode for keyboard typing in ascii")
 
     group = parser.add_argument_group("whisper options")
     group.add_argument("--duration", default=120, type=int, help="Max duration of the whisper recording (default %(default)ss)")
@@ -164,7 +165,7 @@ def get_parser():
 
 
 # Commencer l'enregistrement
-def start_recording(micro, transcriber, clipboard=True, keyboard=False, latency=0, **greetings):
+def start_recording(micro, transcriber, clipboard=True, keyboard=False, latency=0, ascii=False, **greetings):
 
     if keyboard:
         from scribe.keyboard import type_text
@@ -184,7 +185,7 @@ def start_recording(micro, transcriber, clipboard=True, keyboard=False, latency=
             clear_line()
             print(result.get('text'))
             if keyboard:
-                type_text(result['text'] + " ", interval=latency) # Simulate typing
+                type_text(result['text'] + " ", interval=latency, ascii=ascii) # Simulate typing
 
             if clipboard:
                 fulltext += result['text'] + " "
@@ -280,7 +281,7 @@ def main(args=None):
             transcriber = get_transcriber(o, prompt=o.prompt)
         print(f">>> Model {transcriber.model_name} from {transcriber.backend} selected. Keyboard [{'on' if o.keyboard else 'off'}]. Clipboard [{'on' if o.clipboard else 'off'}] <<<")
         if o.prompt:
-            print(f"Choose any of the following actions:")
+            print(f"Choose any of the following actions (or any command-line toggle flag by name)")
             print(f"[q] quit")
             print(f"[e] change model")
             print(f"[x] toggle app [{toggle[o.app]}] -> [{toggle[not o.app]}]")
@@ -290,7 +291,7 @@ def main(args=None):
                 print(f"[t] change duration (currently {transcriber.timeout}s)")
                 print(f"[b] change silence duration (currently {transcriber.silence_duration}s)")
                 print(f"[a] toggle auto-restart after silence [{toggle[transcriber.restart_after_silence]}] -> [{toggle[not transcriber.restart_after_silence]}]")
-            print(colored(f"Press [Enter] or any other key to start recording.", "BOLD"))
+            print(colored(f"Press [Enter] to start recording.", "BOLD"))
 
             key = input()
             if key == "q":
@@ -324,19 +325,27 @@ def main(args=None):
                 except:
                     print("Invalid duration. Must be an integer.")
                 continue
+            if key:
+                if hasattr(o, key) and isinstance(getattr(o, key), bool):
+                    setattr(o, key, not getattr(o, key))
+                    print(f"Toggle {key} to [{getattr(o, key)}].")
+                print(f"Invalid choice: {key}.")
+                continue
 
         if o.app:
             greetings = dict(
                 start_message = "Listening... Use the try icon menu to stop.",
             )
-            app = create_app(micro, transcriber, clipboard=o.clipboard, keyboard=o.keyboard, latency=o.latency, **greetings)
+            app = create_app(micro, transcriber, clipboard=o.clipboard,
+                             keyboard=o.keyboard, latency=o.latency, ascii=o.ascii, **greetings)
             print("Starting app...")
             app.run()
         else:
             greetings = dict(
                 start_message = "Listening... Press Ctrl+C to stop.",
             )
-            start_recording(micro, transcriber, clipboard=o.clipboard, keyboard=o.keyboard, latency=o.latency, **greetings)
+            start_recording(micro, transcriber, clipboard=o.clipboard,
+                            keyboard=o.keyboard, latency=o.latency, ascii=o.ascii, **greetings)
 
         # if we arrived so far, that means we pressed Ctrl + C anyway, and need Enter to move on.
         # So we leave the wider range of options to change the model.

{scribe_cli-0.7.6 → scribe_cli-0.7.7}/scribe/keyboard.py

@@ -2,6 +2,8 @@
 """
 import platform
 import time
+import unidecode
+import logging
 
 try:
     # import pyautogui
@@ -30,11 +32,24 @@ def paste_text():
         keyboard.release('v')
         keyboard.release(Key.ctrl)
 
-def type_text(text, interval=0, paste=False):
+def safe_type_text(text):
+    """I got key errors with the uinput mode, so I'm using unidecode to convert
+    the text to ASCII before typing it."""
+    try:
+        keyboard.type(text)
+    except KeyError:
+        asciitext = unidecode.unidecode(text)
+        logging.warning(f"Key error with {text} -> convert to {asciitext}")
+        keyboard.type(asciitext)
+
+def type_text(text, interval=0, paste=False, ascii=False):
     # Simulate typing a string
     # import subprocess
     # subprocess.run(["ydotool", "type", text])
 
+    if ascii:
+        text = unidecode.unidecode(text)
+
     if paste:
         import pyperclip
         keep_state = pyperclip.paste()
@@ -45,7 +60,9 @@ def type_text(text, interval=0, paste=False):
 
     if interval > 0:
         for c in text:
-            keyboard.type(c)
+            # keyboard.type(c)
+            safe_type_text(c)
             time.sleep(interval)
     else:
-        keyboard.type(text)
+        # keyboard.type(text)
+        safe_type_text(text)

{scribe_cli-0.7.6 → scribe_cli-0.7.7/scribe_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: scribe-cli
-Version: 0.7.6
+Version: 0.7.7
 Summary: scribe is a local speech recognition tool that provides real-time transcription using vosk and whisper AI, with the goal of serving as a virtual keyboard on a computer
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT License
@@ -44,6 +44,7 @@ Requires-Dist: sounddevice
 Requires-Dist: tqdm
 Requires-Dist: requests
 Requires-Dist: pyperclip
+Requires-Dist: unidecode
 Provides-Extra: keyboard
 Requires-Dist: pynput; extra == "keyboard"
 Provides-Extra: whisper
@@ -60,7 +61,7 @@ Requires-Dist: vosk; extra == "all"
 Requires-Dist: pystray; extra == "all"
 
 [![python](https://img.shields.io/badge/python-3.12-blue.svg)]()
-[![pypi](https://github.com/perrette/scribe/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/papers-cli)
+[![pypi](https://github.com/perrette/scribe/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/scribe-cli)
 
 # Scribe
 
@@ -83,7 +84,7 @@ sudo apt-get install portaudio19-dev xclip
 See additional requirements for the [icon tray](#system-tray-icon-experimental) and [keyboard](#virtual-keyboard-experimental) options. The python dependencies should be dealt with automatically:
 
 ```bash
-pip install scribe-cli[all]"
+pip install scribe-cli[all]
 ```
 
 (note the `-cli` suffix for client)
@@ -121,7 +122,7 @@ With the `whisker` model you need to stop the registration manually before the t
 there is a maximum duration after which it will stop by itself, which is setup to 60s by default (unless `--duration` is set to something else).
 
 The `vosk` backend is much faster and very good at doing real-time transcription for one language, but tended to make more mistakes in my tests and it does not do punctuation.
-Use mainly for longer typing session with the [keyboard](#virtual-keyboard-advanced) option, e.g. to make notes.
+It becomes really powerful when used for longer or interactive typing session with the [keyboard](#virtual-keyboard-experimental) option, e.g. to make notes or chat with an AI.
 There are many [vosk models](https://alphacephei.com/vosk/models) available, and here a few are associated to [a handful of languages](scribe/models.toml) `en`, `fr`, `it`, `de` (so far).
 
 To skip the initial selection menu you can do:

{scribe_cli-0.7.6 → scribe_cli-0.7.7}/scribe_cli.egg-info/requires.txt

@@ -3,6 +3,7 @@ sounddevice
 tqdm
 requests
 pyperclip
+unidecode
 
 [all]
 pynput