Downloads · 30 days
0
malayalam_asr_model
abhiramivs/malayalam_asr_model
malayalam_asr_model is a machine learning model from abhiramivs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains a LoRA (Low-Rank Adaptation) fine-tuned adapter for the base model Whisper-small(https://huggingface.co/openai/whisper-small). The adapter is trained on [Malayalam speech data].
Access
Public
Updated Jul 12, 2025
Repo size
33.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt19 MB · 57%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 12, 2025
- Updated
- Jul 12, 2025
- SHA
- 945a67f8
Base models
Model card
From the Hugging Face model README
🔧 LoRA Fine-Tuned Adapter for [Your Task or Dataset Name]
This repository contains a LoRA (Low-Rank Adaptation) fine-tuned adapter for the base model Whisper-small(https://huggingface.co/openai/whisper-small). The adapter is trained on [Malayalam speech data].
🧠 Base Model
- Base Model:
whisper-small - Model Type: Seq2Seq (pick one)
- LoRA Library: PEFT (Hugging Face)
🏋️ Training Details
- Framework: PyTorch + 🤗 Transformers + 🤗 PEFT
- LoRA Config:
r = 32lora_alpha = 64lora_dropout = 0.05bias = "none"- `task_type = None
🧪 How to Use
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("openai/whisper-small")
tokenizer = AutoTokenizer.from_pretrained("openai/whisper-small")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "abhiramivs/malayalam_asr_model")
- License
- apache-2.0
- Languages
- ml
- Created
- Jul 12, 2025
- Updated
- Jul 12, 2025