Downloads · 30 days
26
17% of all-time downloads
Shanmugapriyan/Qwen3-Omni-30B-A3B-Instruct-merged-ft
Qwen3-Omni-30B-A3B-Instruct-merged-ft is a automatic speech recognition model from Shanmugapriyan. Use it when you need speech turned into text. The card lists the license as apache-2.0.
This model is a fine-tuned version of Qwen3-Omni-30B-A3B-Instruct designed for Automatic Speech Recognition (ASR) tasks.
Downloads · 30 days
26
17% of all-time downloads
All-time downloads
152
Public
Parameters
31.7B
63.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors63.4 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of Qwen3-Omni-30B-A3B-Instruct designed for Automatic Speech Recognition (ASR) tasks.
The model was fine-tuned on multilingual speech data containing English and Hindi audio transcripts to improve transcription accuracy.
It can transcribe spoken audio into text and is suitable for:
Base model used:
Qwen/Qwen3-Omni-30B-A3B-Instruct
This model supports multimodal inputs including:
| Property | Value |
|---|---|
| Base Model | Qwen3 Omni 30B |
| Task | Automatic Speech Recognition |
| Languages | English, Hindi |
| Training Method | Fine-tuning |
| Format | Instruction-based training |
| Dataset Format | JSONL |
The model was trained on a dataset containing:
Languages included:
Dataset repository:
Shanmugapriyan/qwen_omni_ft_data
You can use this model for Automatic Speech Recognition.
This model is designed for:
Recommended hardware:
Shanmugapriyan T
AI Engineer | Voice AI Systems | LLM Fine-tuning
Apache 2.0