wenet-e2e / west
We Speech Transcript based on LLM, in 300 lines of code.
☆149Updated 2 weeks ago
Alternatives and similar repositories for west:
Users that are interested in west are comparing it to the libraries listed below
- A toolkit for speaker diarization.☆172Updated 4 months ago
- ☆191Updated 5 months ago
- A lightweight end-to-end text-to-speech model☆110Updated 3 weeks ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆89Updated last month
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆93Updated 3 months ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆86Updated 5 months ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆85Updated last year
- LlamaVoice is a llama-based large voice generation model, providing inference and training ability.☆232Updated 6 months ago
- An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement☆146Updated last week
- Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.☆161Updated 4 months ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆269Updated 2 months ago
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆34Updated 5 months ago
- flow mirror models from JZX AI Labs☆43Updated 5 months ago
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆66Updated this week
- llama-omni训练代码复现☆56Updated 2 months ago
- Huawei Grad-TTS for Chinese☆46Updated last year
- F5-TTS 推理加速,速度提升约4倍!☆59Updated 2 months ago
- ☆157Updated 3 months ago
- A enterprise-grade Chinese-English code switch punctuator from funasr.☆21Updated 10 months ago
- This is the audio sample repository for speech separation model "MossFormer2".☆119Updated 3 months ago
- ☆64Updated last year
- ☆16Updated 4 months ago
- Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆232Updated last week
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆198Updated 2 months ago