Downloads · 30 days
12
12% of all-time downloads
base-bn-lora-adapter-cp10k
Da4ThEdge/base-bn-lora-adapter-cp10k
base-bn-lora-adapter-cp10k is a automatic speech recognition model from Da4ThEdge. Use it when you need speech turned into text. It is set up for peft. The card lists the license as apache-2.0.
This model is a PEFT LoRA fine-tuned version of openai/whisper-base on the Common Voice 17.0 dataset. After 10k steps it achieves the following results on the test set: - Wer: 46.25395 - Normalized Wer: 23.31617
All-time downloads
99
Public
Repo size
4.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.7 MB · 96%
At a glance
- Task
- Automatic Speech Recognition
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- May 5, 2025
- Updated
- May 5, 2025
- SHA
- b0100f7f
Base models
Model card
From the Hugging Face model README
Whisper Base Bn LoRA Adapter (10k steps) - by BanglaBridge
This model is a PEFT LoRA fine-tuned version of openai/whisper-base on the Common Voice 17.0 dataset. After 10k steps it achieves the following results on the test set:
- Wer: 46.25395
- Normalized Wer: 23.31617
Refer to the 20k full-trained adapter repository for more details on the finetuning: banglabridge/base-bn-lora-adapter
Framework versions
- Transformers 4.40.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.19.1
- Peft 0.10.0
- Task
- Automatic Speech Recognition
- Library
- peft
- License
- apache-2.0
- Languages
- bn
- Created
- May 5, 2025
- Updated
- May 5, 2025