slp-rl/slamkit
SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on One GPU in a Day"
SlamKit helps researchers and engineers quickly train and evaluate Speech Language Models using audio-only data. It takes raw audio files or pre-processed audio features and outputs a trained SpeechLM, ready for further use. This toolkit is designed for anyone working on speech recognition, synthesis, or understanding who needs an efficient way to develop and fine-tune large speech models.
229 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer developing Speech Language Models and want to significantly accelerate the training and evaluation process, even on a single GPU.
Not ideal if you are looking for a simple, off-the-shelf solution to use a pre-trained model for inference without needing to train or fine-tune one yourself.
Stars
229
Forks
14
Language
Python
License
MIT
Category
Last pushed
May 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/slp-rl/slamkit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TsinghuaC3I/MARTI
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
zjunlp/KnowLM
An Open-sourced Knowledgable Large Language Model Framework.
cli99/llm-analysis
Latency and Memory Analysis of Transformer Models for Training and Inference
tanyuqian/redco
NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to...
stanleylsx/llms_tool
一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。