speechmatics / ctranslate2_triton_backendLinks
Triton backend for https://github.com/OpenNMT/CTranslate2
☆35Updated last year
Alternatives and similar repositories for ctranslate2_triton_backend
Users that are interested in ctranslate2_triton_backend are comparing it to the libraries listed below
Sorting:
- Triton backend for https://github.com/OpenNMT/CTranslate2☆11Updated 9 months ago
- ☆38Updated 3 years ago
- Final training script from HuggingFace Whisper Fine tuning event - to get best results on finetuned model.☆12Updated 2 years ago
- LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation☆109Updated 2 weeks ago
- Library for pruning experts per language pair in NLLB-200☆33Updated last year
- Fast whitespace correction with Transformers☆16Updated 2 weeks ago
- Text utilities, including beam search decoding, tokenizing, and more, built for use in Flashlight.☆70Updated 3 months ago
- ☆103Updated last week
- Integrating SSE with NVIDIA Triton Inference Server using a Python backend and Zephyr model. There is very less documentation how to use …☆10Updated last year
- Whisper finetuned on VinBigdata-VLSP2020-100h + KenLM☆39Updated last year
- ONNX and TensorRT implementation of Whisper☆63Updated 2 years ago
- ☆46Updated 2 years ago
- Zero-shot Audio Classification using Whisper☆79Updated 2 years ago
- A model that predicts the punctuation of English, Italian, French and German texts.☆80Updated 2 years ago
- Repository containing the open source code of works published at the FBK MT unit.☆44Updated last week
- Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode☆111Updated 2 years ago
- This repository contains data used in the NAACL 2021 Paper - Proteno: Text Normalization with Limited Data for Fast Deployment in Text to…☆45Updated 4 years ago
- Inference script for Meta's LLaMA models using Hugging Face wrapper☆110Updated 2 years ago
- ☆79Updated last year
- Whisper fine-tuning event script to use multiple hf datasets☆32Updated 2 years ago
- ☆43Updated 2 years ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- Repository contains code to fine-tune WhisperASR model☆23Updated 2 years ago
- Audio tokenization, in the fastest way possible!☆52Updated 9 months ago
- A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models☆31Updated 4 years ago
- Transformation spoken text to written text☆30Updated last year
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆89Updated 3 months ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆17Updated 6 months ago
- ☆15Updated 3 months ago
- ☆30Updated 2 years ago