OpenNMT / CTranslate2
Fast inference engine for Transformer models
β3,728Updated this week
Alternatives and similar repositories for CTranslate2:
Users that are interested in CTranslate2 are comparing it to the libraries listed below
- Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.β3,825Updated 3 months ago
- π Accelerate inference and training of π€ Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimizationβ¦β2,841Updated this week
- Whisper realtime streaming for long speech-to-text transcription and translationβ2,729Updated 3 months ago
- A fast inference library for running LLMs locally on modern consumer-class GPUsβ4,101Updated 3 weeks ago
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.β2,856Updated last year
- Large Language Model Text Generation Inferenceβ9,992Updated this week
- Accessible large language models via k-bit quantization for PyTorch.β6,901Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:β2,077Updated this week
- Python bindings for the Transformer models implemented in C/C++ using GGML library.β1,858Updated last year
- Transformer related optimization, including BERT, GPTβ6,116Updated last year
- JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.β4,580Updated last year
- Silero VAD: pre-trained enterprise-grade Voice Activity Detectorβ5,521Updated 3 weeks ago
- Faster Whisper transcription with CTranslate2β15,291Updated 3 weeks ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.β4,802Updated 3 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationβ2,912Updated 2 weeks ago
- Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speakerβ¦β7,255Updated this week
- A nearly-live implementation of OpenAI's Whisper.β2,688Updated this week
- 4 bits quantization of LLaMA using GPTQβ3,050Updated 9 months ago
- Tensor library for machine learningβ12,272Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.β1,999Updated 2 weeks ago
- β‘ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Plβ¦β2,168Updated 6 months ago
- Unified-Modal Speech-Text Pre-Training for Spoken Language Processingβ1,334Updated 11 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.β6,056Updated this week
- A blazing fast inference solution for text embeddings modelsβ3,414Updated this week
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language modelβ1,501Updated 3 weeks ago
- A framework for few-shot evaluation of language models.β8,595Updated this week
- StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelsβ5,630Updated 8 months ago
- Fast and memory-efficient exact attentionβ16,835Updated this week
- Tools for merging pretrained large language models.β5,544Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMsβ10,366Updated 10 months ago