feat: Enhance curated examples display with individual audio players and add a script for parsing results.

i18n

fix: adjust sample display to use multiline Dataframe

Add audio samples separately

feat: app update with UI improvements and example texts

feat: Update Gradio theme, header text, and model description in the 'About' section.

Refactor UI: separate tables and add Advanced Options accordion

fix typo in requirements

Replace UI labels with interactive Top-K DataFrame table

fix: include '@' in family label stripping pattern

Map language code to inali_name and update UI label

Implement LabelExtractor to map predictions back to text labels

Decode output logits to text using tokenizer

refactor

perf: Optimize CPU usage by setting PyTorch threads to 1 and enabling low memory model loading, and remove an unnecessary return.

test pre return2

test pre return

Add persistent UI logging for crash debugging

feat: add audio normalization for int16 and int32 audio input arrays

feat: Add audio resampling to 16kHz before processing to ensure consistent input.

refactor: delegate audio normalization and resampling to the processor.

feat: Add detailed logging for audio processing and inference, remove unused imports, and adjust Gradio launch configuration.

refactor: Remove unused imports and commented code, add detailed logging for audio processing, and update Gradio launch parameters.

import fix

wrong class fix

Refactor: Simplify model loading by directly using `from_pretrained` for `WhisperEncoderOnlyForClassification` and removing explicit config and weight loading.

gpu fixes

import fix

refactor: Streamline model loading by using `load_file` for safetensors and adjusting print statements.

Merge branch 'main' of https://huggingface.co/spaces/tachiwin/classifier

readme fixes

initial commit

initial commit