-
## 🚀 Feature Request
The XLS-R [1] paper demonstrates the performance of the model on the LID task on VoxLingua107 dataset. I am running some model comparisons for the LID task and will appreciate …
-
* See #12 for file format of the input
* Compute Spearman’s rank correlation coefficient between this scoreand the human judgments
* Consider variations to use Euclidean distance and other metri…
-
**Describe the bug**
用其他语种作为prompt_speech_16k进行声音克隆无法实现跨语种
**To Reproduce**
Steps to reproduce the behavior:
1. 导入了一段ずんだもん的日语音频，`日本には四季があり、それぞれの季節に美しい風景や特別な行事があります。`
2. 尝试生成中文语音`”人间灯火倒映湖中，她的渴望让…
-
Hello, I'm trying to use:
- Combined TM on Wikipedia Data (Preproc+Saving+Viz) (stable v2.3.0)
- Zero-Shot Cross-lingual Topic Modeling (Preproc+Viz) (stable v2.3.0)
but always get one or anoth…
-
## 0. Paper
- paper: [link](https://aclanthology.org/2023.acl-long.677/)
- my slide (in Japanese): [link](https://speakerdeck.com/a1da4/wen-xian-shao-jie-whitenedcse-whitening-based-contrastive-…
a1da4 updated
9 months ago
-
It would be useful to monitor not just Wikipedia this way, but all Wikimedia sites, as per [Special:SiteMatrix](https://en.wikipedia.org/wiki/Special:SiteMatrix).
If implementing it for the entire ma…
-
## TODO Languages:
Top languages with at least three tasks per language:
- [ ] Spanish
- [x] https://huggingface.co/datasets/squad_es
- [ ] https://huggingface.co/datasets/ehealth_kd
…
-
**System information**
- Have I written custom code (as opposed to using a stock example script provided in TensorFlow): yes
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04
…
-
Hi all
Thank you for the very helpful package. I am using it to link clinical trials from two databases, one in local language, one in English. Linking is done cross-lingually on the title of the t…
-
I am trying to extract a words embedding of the various tokenized (.tok) files. I have preprocessed the various dataset using preprocessing pipeline suggested in the TransCoder. I have also trained th…