Spaces:

tecasoftai
/

hubert-phoneme-space

Sleeping

App Files Files Community

hubert-phoneme-space / README.md

Nguyen Anh Hong

reupload

a6380bd 9 months ago

preview code

raw

history blame contribute delete

729 Bytes

A newer version of the Gradio SDK is available: 6.14.0

Upgrade

metadata

title: Hubert Phoneme Space
emoji: 🔥
colorFrom: red
colorTo: red
sdk: gradio
sdk_version: 5.38.2
app_file: app.py
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

HuBERT Phoneme Recognition

This Space demonstrates a fine-tuned HuBERT model for phoneme recognition.
Upload or record an audio (16kHz speech), and get the corresponding phoneme sequence (e.g. ARPAbet).

Model: tecasoftai/hubert-finetune
Task: Phoneme recognition (CTC)
Training dataset: Libri
Output format: phoneme sequence string

Usage

Click "Record" or upload a .wav file. The model returns the decoded phonemes.