jiamingkong / slam_asr_pytorchLinks
Re-implementation of SLAM-ASR paper's experiment, using Phi-2 and Hubert
☆21Updated last year
Alternatives and similar repositories for slam_asr_pytorch
Users that are interested in slam_asr_pytorch are comparing it to the libraries listed below
Sorting:
- [ICASSP 2024] KNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels☆42Updated last year
- [ICASSP2023] Source code, model links and open test sets for paper SeACo-Paraformer.☆39Updated last year
- Official implementation for Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning☆96Updated last year
- Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speake…☆57Updated 2 years ago
- 《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》☆77Updated 2 years ago
- TTS FrontEnd DataSet: Polyphone / Prosody / TextNormalization☆103Updated 2 years ago
- E2E TTS using Conditional Flow Matching (Experimental*)☆71Updated 2 years ago
- Unofficial pytorch reproduction for the paper "Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction" (…☆61Updated last year
- ☆68Updated 2 years ago
- [Findings of NAACL 2024] Source code of paper CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers a…☆69Updated last year
- Inference code for Audiodec-Valle-Wenetspeech4TTS☆50Updated last year
- All generative model in one for better TTS model☆74Updated last year
- ☆59Updated 3 months ago
- English conversation corpus for conversational TTS.☆21Updated 2 years ago
- A Neural Audio Codec (NAC) for Universal Audio☆44Updated 8 months ago
- An automatic prosodic boundary annotation tool for Text-to-Speech Synthesis (TTS).☆51Updated last year
- faster inference☆28Updated last year
- Torch Audio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆62Updated 5 months ago
- Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark☆35Updated 8 months ago
- ☆30Updated 7 months ago
- VoiceBank-2023 is the speech corpus specially designed for constructing personalized Mandarin text-to-speech (TTS) systems.☆41Updated last month
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆110Updated 8 months ago
- Speaker-aware CTC (SACTC) for multi-talker overlapped speech recognition.☆21Updated 8 months ago
- The implementation of paper "SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody"☆34Updated 2 years ago
- ☆33Updated 2 years ago
- Compute WER and SER for speech recognition evaluation☆25Updated last month
- ☆29Updated last year
- ☆99Updated 2 weeks ago
- Official release of StyleTalk dataset.☆72Updated last year
- Just another FastSpeech 2 but cleaner code :)☆29Updated last year