Skip to content

final #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
evemak wants to merge 1 commit into
base: main
Choose a base branch
from
Open

final #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1,9 @@
venv/
.venv
.env
.DS_Store
__pycache__/
*.py[cod]
*.mp4
output.wav
en.openfoodfacts.org.products.csv
19 changes: 5 additions & 14 deletions 20_gesutre.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -295,26 +295,17 @@ def text_to_speech(text, voice="en_US/ljspeech_low"):
# Create a temporary file to store audio
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_audio:
output_file = temp_audio.name
# Define Mimic 3 command
mimic3_cmd = [
"mimic3", # Mimic 3 command
"--voice", voice, # Specify the voice
"--stdout", # Output audio to stdout
text # Input text
]
try:
# Generate TTS audio and save it to a temporary file
with open(output_file, "wb") as audio_file:
subprocess.run(mimic3_cmd, stdout=audio_file, check=True)
# Generate TTS audio using kokoro
import sound4567
sound4567.speak(text, output_file=output_file)
# Play the audio using an appropriate command for your OS
if os.name == "posix": # macOS or Linux
os.system(f"afplay {output_file}")
elif os.name == "nt": # Windows
os.system(f"start {output_file}")
except FileNotFoundError:
print("Mimic 3 is not installed or not found in PATH.")
except subprocess.CalledProcessError as e:
print(f"Error generating speech: {e}")
except Exception as e:
print(f"Error generating speech with kokoro: {e}")
finally:
if os.path.exists(output_file):
os.remove(output_file)
Expand Down
Binary file removed __pycache__/directional_audio_generator.cpython-311.pyc
View file
Open in desktop
Binary file not shown.
Binary file removed __pycache__/instrumental_beeping.cpython-311.pyc
View file
Open in desktop
Binary file not shown.
Binary file removed __pycache__/mimic.cpython-311.pyc
View file
Open in desktop
Binary file not shown.
Binary file removed __pycache__/test_stt.cpython-311.pyc
View file
Open in desktop
Binary file not shown.
219 changes: 219 additions & 0 deletions annotations.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,219 @@
<?xml version="1.0" encoding="utf-8"?>
<annotations>
<version>1.1</version>
<meta>
<task>
<id>2048570</id>
<name>vending machine 2</name>
<size>9</size>
<mode>annotation</mode>
<overlap>0</overlap>
<bugtracker></bugtracker>
<created>2026-02-24 16:44:54.578026+00:00</created>
<updated>2026-02-24 16:48:51.747391+00:00</updated>
<subset>default</subset>
<start_frame>0</start_frame>
<stop_frame>8</stop_frame>
<frame_filter></frame_filter>
<segments>
<segment>
<id>3669199</id>
<start>0</start>
<stop>8</stop>
<url>https://app.cvat.ai/api/tasks/2048570/dataset/export/api/jobs/3669580</url>
</segment>
</segments>
<owner>
<username>evelynn</username>
<email>em4829@nyu.edu</email>
</owner>
<assignee></assignee>
<labels>
<label>
<name>0 wrist</name>
<color>#e5c37c</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>1 thumb_cmc</name>
<color>#68b7a4</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>2 thumb_mcp</name>
<color>#7e3ed0</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>3 thumb_ip</name>
<color>#0b0ca4</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>4 thumb_tip</name>
<color>#47dfed</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>5 index_mcp</name>
<color>#f359d1</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>6 index_pip</name>
<color>#23c460</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>7 index_dip</name>
<color>#ab74ee</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>8 index_tip</name>
<color>#2d13f2</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>9 middle_mcp</name>
<color>#aba8cd</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>10 middle_pip</name>
<color>#a96edd</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>11 middle_dip</name>
<color>#386bd2</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>12 middle_tip</name>
<color>#180eb3</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>13 ring_mcp</name>
<color>#387344</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>14 ring_pip</name>
<color>#ca2a68</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>15 ring_dip</name>
<color>#c34055</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>16 ring_tip</name>
<color>#061bbb</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>17 pinky_mcp</name>
<color>#513e06</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>18 pinky_pip</name>
<color>#69cfc8</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>19 pinky_dip</name>
<color>#34d543</color>
<type>any</type>
<attributes>
</attributes>
</label>
<label>
<name>20 pinky_tip</name>
<color>#91ffd4</color>
<type>any</type>
<attributes>
</attributes>
</label>
</labels>
</task>
<dumped>2026-02-24 16:49:41.871327+00:00</dumped>
</meta>
<image id="0" name="Pasted Graphic 1.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="246.42,530.48" z_order="0">
</points>
</image>
<image id="1" name="Pasted Graphic 2.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="562.46,492.86" z_order="0">
</points>
</image>
<image id="2" name="Pasted Graphic 3.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="810.77,522.96" z_order="0">
</points>
</image>
<image id="3" name="Pasted Graphic 4.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="859.68,746.81" z_order="0">
</points>
</image>
<image id="4" name="Pasted Graphic 5.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="543.65,694.14" z_order="0">
</points>
</image>
<image id="5" name="Pasted Graphic 6.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="276.52,692.26" z_order="0">
</points>
</image>
<image id="6" name="Pasted Graphic 7.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="253.95,886.02" z_order="0">
</points>
</image>
<image id="7" name="Pasted Graphic 8.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="504.14,844.63" z_order="0">
</points>
</image>
<image id="8" name="Pasted Graphic.png" width="1078" height="1298">
<points label="8 index_tip" source="manual" occluded="0" points="767.51,280.29" z_order="0">
</points>
</image>
</annotations>
Empty file added demo_camera_2.py
View file
Open in desktop
Empty file.
Loading