An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
-
Updated
Oct 10, 2023 - Python
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
A curated list of research papers and resources on code-switching
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
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.
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
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.
Implementation of meta-transfer-learning for ASR and LM (ACL 2020)
CodeSwitch is a NLP tool, can use for language identification, pos tagging, name entity recognition, sentiment analysis of code mixed data.
Natural Language Procesing
Multilingual Meta-Embeddings for Named Entity Recognition (RepL4NLP & EMNLP 2019)
Pytorch implementation of CS-Tacotron, a code-switching speech synthesis end-to-end generative TTS model.
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.
Supertonic-ZH — fast on-device Mandarin TTS (pure ONNX). Now with streaming synthesis for real-time dialogue (low first-audio latency, barge-in).
A curated list of resources dedicated to Code-mixed Natural Language Processing (NLP).
Kawa is Makimoto's multilingual speech-to-text model, optimised for APAC accents, code-switching and enterprise voice AI applications.
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。
Hierarchical Korean-English Code-Switching Speech Recognition Benchmark (EACL Findings 2026) | 한영 혼용 음성인식 벤치마크
[ACL 2024] 💬 MaskLID: Code-Switching Language Identification through Iterative Masking
Lamitype (formerly HushType): free, privacy-first voice-to-text for macOS. Traditional-Chinese-first, memory-light. Runs Qwen3-ASR locally on Apple Silicon via MLX; optional cloud lane straight to your provider. 免費開源的 Mac 繁體中文語音輸入,本機執行 Qwen3-ASR。
Shruti: 29.5 MB speech-to-text for Hindi, English and Hinglish that runs offline on a phone, a laptop or in the browser. Built on Cactus Whistle. Docs, runnable examples and checksums; weights on Hugging Face.
To associate your repository with the code-switching topic, visit your repo's landing page and select "manage topics."