scribe-cli 0.5.0__tar.gz → 0.5.1__tar.gz

{scribe_cli-0.5.0/scribe_cli.egg-info → scribe_cli-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: scribe-cli
-Version: 0.5.0
+Version: 0.5.1
 Summary: scribe is a local speech recognition tool that provides real-time transcription using vosk and whisper AI.
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT License

{scribe_cli-0.5.0 → scribe_cli-0.5.1}/scribe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.5.0'
-__version_tuple__ = version_tuple = (0, 5, 0)
+__version__ = version = '0.5.1'
+__version_tuple__ = version_tuple = (0, 5, 1)

{scribe_cli-0.5.0 → scribe_cli-0.5.1}/scribe/models.py

@@ -1,6 +1,7 @@
 import os
 import json
 import numpy as np
+import time
 from scribe.util import download_model
 
 VOSK_MODELS_FOLDER = os.path.join(os.environ.get("HOME"),
@@ -9,21 +10,22 @@ VOSK_MODELS_FOLDER = os.path.join(os.environ.get("HOME"),
 
 class AbstractTranscriber:
     backend = None
-    def __init__(self, model, model_name=None, language=None, samplerate=16000, max_duration=None, model_kwargs={}):
+    def __init__(self, model, model_name=None, language=None, samplerate=16000, timeout=None, model_kwargs={}):
         self.model_name = model_name
         self.language = language
         self.model = model
         self.model_kwargs = model_kwargs
         self.samplerate = samplerate
-        self.max_duration = max_duration
+        self.timeout = timeout
         self.one_second_bytes = self.samplerate * 2 # 16-bit audio, 1 channel  ~ 32000 bytes
         self.audio_buffer = b''
+        self.start_time = time.time()
 
-    def get_elapsed(self, size=None):
-        return len(size or self.audio_buffer) / self.one_second_bytes
+    def get_elapsed(self):
+        return time.time() - self.start_time
 
-    def is_overtime(self, elapsed=None, size=None):
-        return self.max_duration and (elapsed or self.get_elapsed(size)) > self.max_duration
+    def is_overtime(self):
+        return time.time() - self.start_time > self.timeout
 
     def transcribe_realtime_audio(self, audio_bytes=b""):
         self.audio_buffer += audio_bytes

{scribe_cli-0.5.0 → scribe_cli-0.5.1}/scribe/streamer.py

@@ -152,7 +152,7 @@ def get_transcriber(o, prompt=True):
             transcriber = VoskTranscriber(model_name=model,
                                         language=o.language,
                                         samplerate=o.samplerate,
-                                        max_duration=None, # vosk keeps going (no timeout)
+                                        timeout=None, # vosk keeps going (no timeout)
                                         model_kwargs={"data_folder": o.data_folder})
         except Exception as error:
             print(error)
@@ -160,7 +160,7 @@ def get_transcriber(o, prompt=True):
             exit(1)
 
     elif backend == "whisper":
-        transcriber = WhisperTranscriber(model_name=model, language=o.language, samplerate=o.samplerate, max_duration=o.duration)
+        transcriber = WhisperTranscriber(model_name=model, language=o.language, samplerate=o.samplerate, timeout=o.duration)
 
     else:
         raise ValueError(f"Unknown backend: {backend}")
@@ -216,7 +216,7 @@ def main(args=None):
             print(f"[k] toggle keyboard [{'off' if o.keyboard else 'on'}]")
             print(f"[c] toggle clipboard [{'off' if o.clipboard else 'on'}]")
             if transcriber.backend == "whisper":
-                print(f"[t] change duration (currently {transcriber.max_duration}s)")
+                print(f"[t] change duration (currently {transcriber.timeout}s)")
             print(colored(f"Press [Enter] or any other key to start recording.", "BOLD"))
 
             key = input()
@@ -232,9 +232,9 @@ def main(args=None):
                 o.clipboard = not o.clipboard
                 continue
             if key == "t":
-                duration = input(f"Enter new duration in seconds (current: {transcriber.max_duration}): ")
+                duration = input(f"Enter new duration in seconds (current: {transcriber.timeout}): ")
                 try:
-                    o.duration = transcriber.max_duration = int(duration)
+                    o.duration = transcriber.timeout = int(duration)
                 except:
                     print("Invalid duration. Must be an integer.")
                 continue

{scribe_cli-0.5.0 → scribe_cli-0.5.1/scribe_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: scribe-cli
-Version: 0.5.0
+Version: 0.5.1
 Summary: scribe is a local speech recognition tool that provides real-time transcription using vosk and whisper AI.
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT License