Model Information
This is the version of meetween/Llama-speechlmm-1.0-l that was fine-tuned for Speech Summarization.
License: see LICENSE
Model Architecture
Identical to base model. This model does not include a video adapter.
This model was obtained by fine-tuning the adapter and a LoRA on the decoder. This repository contains the weights with the LoRA merged into the main weights.
How to Use
Identical to base model.
Training Data
This model has been fine-tuned on the same AMI and ICSI speech summarization data from the training data of the base model.
Evaluation Results
| Model Name | Topic Segmentation |
Summary of Summaries |
ICSI | ||
|---|---|---|---|---|---|
| R-1 | R-2 | R-L | |||
| Cascade (Whisper + Textual summ.) | |||||
| Base Model | No | No | 27.6 | 3.8 | 25.3 |
| Base Model | Yes | No | 25.9 | 5.3 | 23.8 |
| Base Model | Yes | Yes | 21.1 | 2.3 | 18.3 |
| meetween/Llama-speechlmm-1.0-l-TSUM | No | No | 31.0 | 4.3 | 27.6 |
| This Model | No | No | 28.9 | 3.8 | 26.0 |
| end-to-end directly from audio | |||||
| Base Model | N/A | N/A | 26.6 | 3.5 | 23.9 |
| +LoRA decoder | N/A | N/A | 27.9 | 3.3 | 25.2 |
| +adapter finetune +LoRA decoder (this model) | No | No | 32.1 | 4.1 | 29.1 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.3.1+cu124.post2
- Datasets 3.2.0
- Tokenizers 0.20.0
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support