Update README.md

README.md

@@ -34,7 +34,7 @@ huggingface-cli download facebook/w2v-bert-2.0 --local-dir w2v-bert-2.0
 huggingface-cli download amphion/dualcodec esdcodec_25hz_16384_1024.safetensors w2vbert2_mean_var_stats_emilia.pt --local-dir esdcodec_ckpts
 
 2. To run example inference:
-```
+```bash
 python infer.py
 ```
 
@@ -52,3 +52,27 @@ cd ESDCodec
 /path/to/your/yyy.tar
 ...
 ```
+
+3. To run example training on Emilia dataset
+```bash
+accelerate launch train.py --config-name=esdcodec_train \
+trainer.batch_size=3 \
+data.segment_speech.segment_length=96000
+```
+
+### Acknowledgement
+This repo is directly based on the following excellent projects:
+
+- [**DualCodec**](https://github.com/jiaqili3/DualCodec)
+- [**SCNet**](https://github.com/vspeech/SCNet)
+
+
+## Citation
+```
+@inproceedings{esdcodec,
+  title     = {ESDCodec: High-Fidelity Neural Speech Codec via Thoroughly Enhanced Semantic Quantizer and Decoder},
+  author    = {Nan Xu, Zhaolong Huang},
+  booktitle = {Proceedings of Interspeech 2026},
+  year      = {2026}
+}
+```