Hugging Face's logo

Spaces:
GavinHuang
/
asr-demo
Running on Zero

App Files Community
asr-demo / app.py

Commit History

switch tabs
bde342d
Running

GavinHuang commited on

fix: add waveform options with sample rate to microphone input for improved audio visualization
04c6dbe

GavinHuang commited on

fix: remove samplerate parameter from microphone input for clarity
89f4303

GavinHuang commited on

fix: add support for additional model in available models and improve audio processing logic
7925ca5

GavinHuang commited on

fix: remove interactivity from audio input components for clarity
944e4f0

GavinHuang commited on

fix: make audio input components interactive based on model availability
2804592

GavinHuang commited on

fix: update transcription handling to return last transcription and improve state management
8d5b897

GavinHuang commited on

fix: correct formatting for instructions section in Gradio interface
2b1f9fe

GavinHuang commited on

fix: add clear transcription functionality for real-time and file transcription, update UI elements
6dbf680

GavinHuang commited on

fix: improve audio processing in transcribe function with longer chunk duration and normalization
f374409

GavinHuang commited on

feat: add file transcription functionality and enhance UI for model selection
2b5f9bc

GavinHuang commited on

fix: correct indentation for instructions markdown in Gradio interface
50ea265

GavinHuang commited on

fix: enhance model loading and selection in transcribe function for improved user experience
2647bd6

GavinHuang commited on

fix: load model inside transcribe function to ensure availability during audio processing
895c600

GavinHuang commited on

fix: enhance audio processing in transcribe function with improved buffering and chunk handling
b407959

GavinHuang commited on

fix: enhance audio processing in transcribe function with librosa and improve transcription output
8505a8f

GavinHuang commited on

fix: streamline transcription process by removing NumPy 2.0 compatibility handling
31b10c8

GavinHuang commited on

fix: add debug prints for transcription type and new state in transcribe function
4be17d8

GavinHuang commited on

fix: move numpy and soundfile imports inside transcribe function and clean up audio buffer handling
692769a

GavinHuang commited on

fix: refactor model loading and enhance error handling in transcribe function
a2ed037

GavinHuang commited on

fix: add librosa import for audio processing functionality
26fc80f

GavinHuang commited on

fix: clean up commented code in transcribe function for clarity
4d5cbf1

GavinHuang commited on

fix: add error handling in transcribe function for audio processing and resampling
c699992

GavinHuang commited on

fix: enhance audio processing in transcribe function to handle tuple input and resample to 16kHz
ac5f4c0

GavinHuang commited on

fix: update tuple audio input handling in transcribe function to extract second element and skip empty tuples
1e2be4f

GavinHuang commited on

fix: update tuple audio input handling in transcribe function to extract second element
ce364ed

GavinHuang commited on

fix: handle tuple audio input in transcribe function and skip empty tuples
615813d

GavinHuang commited on

fix: add logging for received audio input type and shape in transcribe function
b6fdfee

GavinHuang commited on

fix: enhance transcription process with audio feedback and temporary file management
0011522

GavinHuang commited on

fix: improve audio processing in transcribe function and add soundfile dependency
779d79b

GavinHuang commited on

fix: enhance audio input handling in transcribe function
fe027e3

GavinHuang commited on

fix: declare model as global in transcribe function for proper access
d7d7874

GavinHuang commited on

refactor model loading and reintroduce GPU decorator for transcription function
f334b99

GavinHuang commited on

update README for real-time speech-to-text application and remove spaces.GPU decorator from load_model function
4efbce4

GavinHuang commited on

add spaces import and reintroduce GPU decorator for model loading
bb03f90

GavinHuang commited on

fix indentation in Gradio interface setup
40dfec3

GavinHuang commited on

update Gradio version in requirements and fix indentation in transcribe function
8c34a9f

GavinHuang commited on

remove spaces.GPU decorator from load_model function and update requirements to include cuda-python
1ffedb9

GavinHuang commited on

add actual code
18b21ee

GavinHuang commited on

deployment try
e888ead

GavinHuang commited on