An awesome spoken LID repository. (Working in progress
-
Updated
Apr 22, 2024 - Python
#
spoken-language-identification
Here are 20 public repositories matching this topic...
End-to-end spoken language identification out of the box.
big-data deep-learning tensorflow speech audio-analysis language-recognition language-identification spoken-language-recognition spoken-language-identification
-
Updated
Dec 13, 2020 - Python
Spoken Language Identification on Common Voice and AudioSet using Deep Learning
lid language-identification audioset common-voice zkm spoken-language-identification intelligent-museum
-
Updated
Feb 4, 2026 - Python
Tidy Tunes is an easy-to-use pipeline for mining high-quality audio data for speech generation models. To do so, it chains multiple open source models while minimizing dependencies.
speech mos vad youtube-downloader data-cleaning source-separation cross-talk spoken-language-identification
-
Updated
May 19, 2026 - Python
kaldi language-recognition language-identification kaldi-asr spoken-language-recognition spoken-language-identification
-
Updated
Jul 8, 2021 - C++
PHO-LID: A Unified Model to Incorporate Acoustic-Phonetic and Phonotactic Information for Language Identification
-
Updated
Aug 24, 2023 - Python
A pipeline to isolate and transcribe one language in mixed-language speech
automatic-speech-recognition endangered-languages voice-activity-detection low-resource-languages spoken-language-identification
-
Updated
Oct 25, 2022 - Python
Source code of paper <End-to-End Language Diarization for Bilingual Code-switching Speech>
-
Updated
Jan 23, 2022 - Python
The official implementation of the method discussed in the paper Improving Spoken Language Identification with Map-Mix(work accepted at ICASSP-2023)
speech-processing datamaps language-identification mixup spoken-language-recognition spoken-language-identification hubert wav2vec2 xlsr confidence-labels
-
Updated
Feb 17, 2023
An Web application Language Identification project uses Pytorch and Torchaudio to accurately identify spoken language from audio files.
nlp language-detection cnn audio-processing cnn-classification spoken-language-recognition spoken-language-identification
-
Updated
Jan 22, 2023 - Python
An object model to the Ethnologue project for Pharo
-
Updated
Aug 23, 2022 - Smalltalk
End-to-end audio ML pipeline for Spoken Language Identification (SLID) across 4 languages using MFCC/Chroma feature extraction, SVM, Random Forest, and LightGBM.
python machine-learning scikit-learn speech-recognition lightgbm mfcc librosa audio-processing spoken-language-identification
-
Updated
Sep 22, 2026 - Jupyter Notebook
Spoken language identification and clustering across 4 languages (German, Italian, Korean, Spanish) using audio feature extraction (MFCCs, Chroma), SVM, Random Forest, GMM, and t-SNE.
-
Updated
May 20, 2026 - Jupyter Notebook
Experiment configuration and metadata
-
Updated
Dec 13, 2020 - Python
-
Updated
Apr 19, 2020
This repository contains the files for the final project of the machine learning course.
-
Updated
Feb 25, 2026 - Jupyter Notebook
End-to-end spoken language identification (German/Italian/Korean/Spanish) from raw audio: MFCC-based feature engineering, leakage-free group splits, KNN/RF/SVM benchmarks and unsupervised clustering analysis.
python machine-learning random-forest clustering svm mfcc audio-classification knn librosa speech-processing spoken-language-identification
-
Updated
Aug 10, 2026 - Jupyter Notebook
Spoken language identification DNN implemented in mxnet
-
Updated
Jul 4, 2021 - Python
A classical machine learning project for identifying the spoken language of audio recordings using engineered acoustic features. The project was developed as a final project for a Machine Learning course and includes both supervised classification and unsupervised clustering of multilingual speech.
machine-learning jupyter-notebook feature-extraction classification unsupervised-learning mfcc audio-classification librosa speech-processing clustring spoken-language-identification sickit-learn
-
Updated
Oct 8, 2026 - Jupyter Notebook
Detects the spoken language in an audio clip using Meta's mms-lid-4017, with a microphone demo and a fine-tuning experiment. Built at GRN Hack 2025.
python machine-learning deep-learning hackathon transformers pytorch speech-recognition transfer-learning audio-classification language-identification endangered-languages huggingface spoken-language-identification wav2vec2
-
Updated
Jul 31, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the spoken-language-identification topic, visit your repo's landing page and select "manage topics."