dora-microphone 0.3.6__tar.gz → 0.3.7rc1__tar.gz

{dora_microphone-0.3.6 → dora_microphone-0.3.7rc1}/PKG-INFO

@@ -1,24 +1,21 @@
 Metadata-Version: 2.1
 Name: dora-microphone
-Version: 0.3.6
+Version: 0.3.7rc1
 Summary: Dora dora-microphone
 Home-page: https://github.com/dora-rs/dora.git
 License: MIT
 Author: Haixuan Xavier Tao
 Author-email: tao.xavier@outlook.com
+Requires-Python: >=3.7,<4.0
 Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 2
-Classifier: Programming Language :: Python :: 2.7
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.4
-Classifier: Programming Language :: Python :: 3.5
-Classifier: Programming Language :: Python :: 3.6
 Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: dora-rs (>=0.3.6,<0.4.0)
 Requires-Dist: numpy (<2.0.0)
 Requires-Dist: pyarrow (>=5.0.0)

dora_microphone-0.3.7rc1/dora_microphone/main.py

@@ -0,0 +1,36 @@
+import sounddevice as sd
+import numpy as np
+import pyarrow as pa
+import time as tm
+import os
+
+from dora import Node
+
+MAX_DURATION = float(os.getenv("MAX_DURATION", "0.1"))
+SAMPLE_RATE = int(os.getenv("SAMPLE_RATE", "16000"))
+
+
+def main():
+    # Initialize buffer and recording flag
+    buffer = []
+    start_recording_time = tm.time()
+    node = Node()
+
+    # pylint: disable=unused-argument
+    def callback(indata, frames, time, status):
+        nonlocal buffer, node, start_recording_time
+
+        if tm.time() - start_recording_time > MAX_DURATION:
+            audio_data = np.array(buffer).ravel().astype(np.float32) / 32768.0
+            node.send_output("audio", pa.array(audio_data))
+            buffer = []
+            start_recording_time = tm.time()
+        else:
+            buffer.extend(indata[:, 0])
+
+    # Start recording
+    with sd.InputStream(
+        callback=callback, dtype=np.int16, channels=1, samplerate=SAMPLE_RATE
+    ):
+        while True:
+            sd.sleep(int(100 * 1000))

{dora_microphone-0.3.6 → dora_microphone-0.3.7rc1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dora-microphone"
-version = "0.3.6"
+version = "0.3.7rc1"
 authors = [
     "Haixuan Xavier Tao <tao.xavier@outlook.com>",
     "Enzo Le Van <dev@enzo-le-van.fr>",
@@ -17,6 +17,7 @@ dora-rs = "^0.3.6"
 numpy = "< 2.0.0"
 pyarrow = ">= 5.0.0"
 sounddevice = "^0.4.6"
+python = "^3.7"
 
 [tool.poetry.scripts]
 dora-microphone = "dora_microphone.main:main"
@@ -24,6 +25,3 @@ dora-microphone = "dora_microphone.main:main"
 [build-system]
 requires = ["poetry-core>=1.8.0"]
 build-backend = "poetry.core.masonry.api"
-
-[project]
-readme = "README.md"

dora_microphone-0.3.6/dora_microphone/main.py

@@ -1,62 +0,0 @@
-import sounddevice as sd
-import numpy as np
-import pyarrow as pa
-import time as tm
-from enum import Enum
-
-from dora import Node
-
-
-class RecordingState(Enum):
-    """Enum for recording states."""
-
-    PENDING = 0
-    RUNNING = 1
-    SILENCE = 2
-
-
-def detect_speech(audio_data, threshold):
-    """Check if the amplitude of the audio signal exceeds the threshold."""
-    return np.any(np.abs(audio_data) > threshold)
-
-
-def main():
-    # Parameters
-    threshold = 500  # Threshold for detecting speech (adjust this as needed)
-    SAMPLE_RATE = 16000
-    silence_duration = 0.5  # Duration of silence before stopping the recording
-
-    # Initialize buffer and recording flag
-    buffer = []
-    state = RecordingState.PENDING
-    silence_start_time = tm.time()
-    node = Node()
-
-    # pylint: disable=unused-argument
-    def callback(indata, frames, time, status):
-        nonlocal buffer, state, silence_start_time, node
-
-        is_speaking = detect_speech(indata[:, 0], threshold)
-        if is_speaking:
-            if state == RecordingState.PENDING:
-                buffer = []
-                state = RecordingState.RUNNING
-            buffer.extend(indata[:, 0])
-        elif not is_speaking and state == RecordingState.RUNNING:
-            silence_start_time = tm.time()  # Reset silence timer
-            buffer.extend(indata[:, 0])
-            state = RecordingState.SILENCE
-        elif not is_speaking and state == RecordingState.SILENCE:
-            if tm.time() - silence_start_time > silence_duration:
-                audio_data = np.array(buffer).ravel().astype(np.float32) / 32768.0
-                node.send_output("audio", pa.array(audio_data))
-                state = RecordingState.PENDING
-            else:
-                buffer.extend(indata[:, 0])
-
-    # Start recording
-    with sd.InputStream(
-        callback=callback, dtype=np.int16, channels=1, samplerate=SAMPLE_RATE
-    ):
-        while True:
-            sd.sleep(int(100 * 1000))