mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-12-11 06:55:27 +00:00
915e8e399c
- Added CHiME-4 dataset integration in asr_datamodule.py - Added Hugging Face upload script - Added RIR augmentation - Added Self-Distillation Training
21 lines
909 B
Markdown
Executable File
21 lines
909 B
Markdown
Executable File
|
|
# Introduction
|
|
|
|
This recipe includes scripts for training [Qwen-Audio](https://github.com/QwenLM/Qwen-Audio/tree/main) style model using multiple datasets.
|
|
|
|
<br>
|
|
<p align="center">
|
|
<img src="assets/framework.png" width="800"/>
|
|
<p>
|
|
<br>
|
|
|
|
[./RESULTS.md](./RESULTS.md) contains the latest results.
|
|
|
|
# ASR_LLM
|
|
|
|
The following table lists the folders for different tasks.
|
|
|
|
| | Speech Encoder | LLM | Comment |
|
|
|---------------------------------------|---------------------|--------------------|---------------------------------------------------|
|
|
| [whisper_llm_zh](./whisper_llm_zh) | Whisper | Qwen2 | [Using multiple Chinese datasets](https://github.com/k2-fsa/icefall/tree/master/egs/multi_zh-hans/ASR) |
|