An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
-
Updated
Oct 10, 2023 - Python
#
code-switching
Here are 183 public repositories matching this topic...
A curated list of research papers and resources on code-switching
-
Updated
Jan 31, 2026
Thai + English voice typing for Mac. Offline speech-to-text that types Thai-spoken tech words in English. Push-to-talk dictation on Apple Silicon (Whisper + MLX), free & open-source Wispr Flow alternative · พิมพ์ด้วยเสียงภาษาไทย
macos swift rust privacy offline speech-recognition speech-to-text thai dictation push-to-talk thai-nlp whisper mlx voice-to-text code-switching on-device-ai apple-silicon voice-typing local-ai wispr-flow-alternative
-
Updated
Oct 31, 2026 - Swift
This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalence Constant Theory and Matrix Language Theory.
natural-language-processing language-modeling python3 linguistics data-generation code-mixing code-switching synthetic-data-generation
-
Updated
Jul 30, 2024 - Jupyter Notebook
This code provides word level language identification tool for identifying language for individual words in Code-Mixed text. e.g. The text that includes words from two languages such as Hindi written in roman script, mixed with English.
natural-language-processing python3 linguistics mallet language-identification language-tags code-mixing code-switching
-
Updated
Aug 11, 2020 - Python
Implementation of meta-transfer-learning for ASR and LM (ACL 2020)
language neural-network multi-lingual acl speech pytorch transformer speech-recognition language-model asr meta-learning code-switching mixed-language meta-transfer-learning
-
Updated
Jul 30, 2020 - Python
VoiceTut-TTS is an Egyptian-Arabic text-to-speech system fine-tuned from OmniVoice on ~380 hours of Egyptian podcast speech. It produces natural Egyptian speech with seamless Arabic ↔ English code-switching, ships 15 built-in studio voices, supports zero-shot voice cloning
text-to-speech streaming tts text-processing speech-processing audio-processing arabic-nlp arabic-language code-switching egyptian-arabic omnivoice voicetut-tts voicetut egyptian-text-to-speech egypt-tts egyptian-tts egyptian-code-switching
-
Updated
Oct 19, 2026 - Python
CodeSwitch is a NLP tool, can use for language identification, pos tagging, name entity recognition, sentiment analysis of code mixed data.
nlp sentiment-analysis transformers pos ner pos-tagging language-identification code-switching hindi-english code-mixed codeswitch huggingface spanish-english
-
Updated
Nov 2, 2020 - Jupyter Notebook
Natural Language Procesing
nlp machine-learning natural-language-processing deep-learning paper machine-translation artificial-intelligence dataset nlp-resources embedding nlp-machine-learning code-switching
-
Updated
Apr 7, 2021
Multilingual Meta-Embeddings for Named Entity Recognition (RepL4NLP & EMNLP 2019)
-
Updated
Oct 11, 2022 - Python
Pytorch implementation of CS-Tacotron, a code-switching speech synthesis end-to-end generative TTS model.
text-to-speech dsp tts speech-synthesis digital-signal-processing ntu tacotron ntuee chinese-english code-switching code-switch
-
Updated
Mar 14, 2019 - Python
QwenCleo-ASR is the currently State-Of-The-Art (SOTA) open-source model for Egyptian Arabic & code-switching speech recognition Built on Qwen3-ASR-1.7B, fine-tuned for Egyptian dialect and Arabic ↔ English code-switching.
streaming speech-recognition automatic-speech-recognition speech-to-text whisper asr egypt arabic-nlp state-of-the-art code-switching arabic-code-switching arabic-speech-recognition vllm qwen nemotron egyptian-speech qwen3-asr cohere-transcribe-03-2026 egyptian-asr
-
Updated
Jun 17, 2026 - Python
Supertonic-ZH — fast on-device Mandarin TTS (pure ONNX). Now with streaming synthesis for real-time dialogue (low first-audio latency, barge-in).
text-to-speech streaming ai deep-learning voice tts speech-synthesis chinese mandarin onnx on-device code-switching mandarin-tts chinese-tts supertonic
-
Updated
Aug 15, 2026 - Python
A curated list of resources dedicated to Code-mixed Natural Language Processing (NLP).
-
Updated
Oct 15, 2026
Kawa is Makimoto's multilingual speech-to-text model, optimised for APAC accents, code-switching and enterprise voice AI applications.
machine-learning deep-learning speech-recognition automatic-speech-recognition speech-to-text transcription audio-processing asr code-switching voice-processing voice-ai multilingual-ai
-
Updated
Oct 29, 2026 - Python
中英混著講，落下的是乾淨的繁體中文。macOS 選單列語音輸入，whisper.cpp 全程在本機跑，kubectl、Terraform 這類術語內建修正。
macos swift productivity menubar privacy offline speech-recognition traditional-chinese speech-to-text opencc dictation push-to-talk whisper zh-tw voice-to-text macos-app code-switching on-device-ai whisper-cpp
-
Updated
Sep 3, 2026 - Swift
Hierarchical Korean-English Code-Switching Speech Recognition Benchmark (EACL Findings 2026) | 한영 혼용 음성인식 벤치마크
-
Updated
Apr 13, 2026 - Python
[ACL 2024] 💬 MaskLID: Code-Switching Language Identification through Iterative Masking
language-identification code-mixing code-switching language-identification-toolkit code-switch language-identifier
-
Updated
Jun 11, 2024 - Python
EduMIND — Multimodal Bilingual Lecture Assistant with Anti-Forget RAG, Whisper ASR, VietMix NMT (CMI-aware), and Human-in-the-Loop Active Learning via Label Studio. Built for code-mixed Vietnamese–English academic environments.
python nlp docker machine-translation speech-recognition whisper active-learning vietnamese-nlp human-in-the-loop bilingual education-technology multimodal code-switching rag label-studio streamlit vector-database qdrant langchain
-
Updated
Jun 23, 2026 - Python
Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching TTS (EMNLP 2026)
-
Updated
Sep 29, 2026 - Python
Add this topic to your repo
To associate your repository with the code-switching topic, visit your repo's landing page and select "manage topics."