Identical to the base model. The model was obtained by training LoRA and the modality adapter on the LLM. This repository contains the model weights with LoRA merged into the main weights.

How to Use

Identical to the base model.

Fine-tuning Data

This model has been fine-tuned on the same data from the training data of the base model.

Evaluation Results

Model Name	Word Error Rate
AV-Hubert	36.41
SpeechLMM_v1.0_L	45.44
SpeechLMM_v1.0_L_LIPREAD	43.06

Framework Versions

Transformers 4.45.0
Pytorch 2.3.1+cu124.post2
Datasets 3.2.0
Tokenizers 0.20.0

meetween/Llama-speechlmm-1.0-l-LIPREAD

Model Information

Model Architecture

How to Use

Fine-tuning Data

Evaluation Results

Framework Versions

meetween/
Llama-speechlmm-1.0-l-LIPREAD