cnlinxi

你好，能否提供TFRecord的写入函数？我不是很明白对于一个样本而言，label/ids/values是怎样的，感谢:)

I see [this issue](https://github.com/microsoft/UniSpeech/issues/27#issuecomment-1178617751): > the recipe for ASR fine-tuning can be found in [fairseq repo](https://github.com/facebookresearch/fairseq/tree/main/examples/hubert). but there is no config file. Can you give a simple example? Thanks a...

Retraining vocoder (hifigan) and dvae in XTTS

6

**🚀 Feature Description** Thank you for your contributing! What is the way to retrain HiFiGAN and DVAE in XTTS v2.0? If I want to use a new training set, but...

According to https://github.com/espeak-ng/espeak-ng/blob/master/docs/dictionary.md#special-characters-in-phoneme-string In the dictionary, we can do this by specifying some words as foreign words. How to specify some words as foreign words without modifying the dictionary file....

Hi, I want to slow down audio and run ```shell ./sonic -s 0.8 in.wav out.wav ``` but introducing abnormal ending:  Is it a bug? Thanks for reply

Why open transactions (txn) repeatedly?

1

```python txn = db.begin(write=True) for idx, data in enumerate(data_loader): # print(type(data), data) image, label = data[0] txn.put(u'{}'.format(idx).encode('ascii'), dumps_pyarrow((image, label))) if idx % write_frequency == 0: print("[%d/%d]" % (idx, len(data_loader))) txn.commit()...

### Before Asking 在提问之前 - [x] I have read the [README](https://github.com/alibaba/data-juicer/blob/main/README.md) carefully. 我已经仔细阅读了 [README](https://github.com/alibaba/data-juicer/blob/main/README_ZH.md) 上的操作指引。 - [x] I have pulled the latest code of main branch to run again and...

The trained LLaMA-MLP-MoE (2/8) cannot generate the correct output

2

Hello authors. I tried to train LLaMA-MLP-MoE (2/8). After two stages of training, the model cannot output normal sentences. The inference script is as follows: ```python model_dir = "" tokenizer...