Downloads · 30 days
9
9% of all-time downloads
Llama-speechlmm-1.0-l-ST
meetween/Llama-speechlmm-1.0-l-ST
Llama-speechlmm-1.0-l-ST is a translation model from meetween. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as other.
This is the version of meetween/Llama-speechlmm-1.0-l that was fine-tuned for Speech-to-Text Translation.
All-time downloads
99
Public
Parameters
9B
18 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors18 GB · 100%
Parameter types
How the weights are stored.
BF169B · 100%
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Model Information
This is the version of meetween/Llama-speechlmm-1.0-l that was fine-tuned for Speech-to-Text Translation.
License: see LICENSE
Model Architecture
Identical to the base model. The model was obtained by training LoRA 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 EuroParl-ST and CoVoST2 speech translation data ({en, fr, it, de, es} → {en, fr, it, de, es}) from the training data of the base model.
Evaluation Results
<style type="text/css"> .tg {border-collapse:collapse;border-spacing:0;} .tg td{border-color:black;border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px; overflow:hidden;padding:10px 5px;word-break:normal;} .tg th{border-color:black;border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px; font-weight:normal;overflow:hidden;padding:10px 5px;word-break:normal;} .tg .tg-8bgf{border-color:inherit;font-style:italic;text-align:center;vertical-align:top} .tg .tg-7btt{border-color:inherit;font-weight:bold;text-align:center;vertical-align:top} .tg .tg-0pky{border-color:inherit;text-align:left;vertical-align:top} .tg .tg-fymr{border-color:inherit;font-weight:bold;text-align:left;vertical-align:top} </style> <table class="tg"><thead> <tr> <th class="tg-7btt">DATASET:</th> <th class="tg-7btt" colspan="5">CoVoST2</th> <th class="tg-7btt" colspan="2">ACL 60/60</th> <th class="tg-7btt" rowspan="2">AVG</th> </tr> <tr> <th class="tg-7btt">BLEU</th> <th class="tg-8bgf">en-de</th> <th class="tg-8bgf">de-en</th> <th class="tg-8bgf">es-en</th> <th class="tg-8bgf">fr-en</th> <th class="tg-8bgf">it-en</th> <th class="tg-8bgf">en-fr</th> <th class="tg-8bgf">en-de</th> </tr></thead> <tbody> <tr> <td class="tg-0pky">SeamlessM4T </td> <td class="tg-0pky">-</td> <td class="tg-0pky">-</td> <td class="tg-0pky">-</td> <td class="tg-0pky">-</td> <td class="tg-0pky">-</td> <td class="tg-fymr">40.4</td> <td class="tg-0pky">28.0</td> <td class="tg-0pky">-</td> </tr> <tr> <td class="tg-0pky">SpeechLMM_v1.0_L</td> <td class="tg-0pky">31.1</td> <td class="tg-0pky">36.2</td> <td class="tg-0pky">41.1</td> <td class="tg-fymr">39.0</td> <td class="tg-fymr">32.5</td> <td class="tg-0pky">29.1</td> <td class="tg-0pky">27.6</td> <td class="tg-0pky">33.8</td> </tr> <tr> <td class="tg-0pky">SpeechLMM_v1.0_L_ST</td> <td class="tg-fymr">33.7</td> <td class="tg-fymr">36.7</td> <td class="tg-fymr">41.5</td> <td class="tg-fymr">39.0</td> <td class="tg-0pky">32.4</td> <td class="tg-0pky">29.6</td> <td class="tg-fymr">28.5</td> <td class="tg-fymr">34.5</td> </tr> </tbody></table>Framework Versions
- Transformers 4.45.0
- Pytorch 2.3.1+cu124.post2
- Datasets 3.2.0
- Tokenizers 0.20.0
- Task
- Translation
- Library
- transformers
- Type
- speechlmm
- License
- other
- Languages
- es, it, en, fr, de
- Created
- Apr 18, 2025
- Updated
- Apr 30, 2025