qwen-tts 0.0.4__py3-none-any.whl → 0.0.5__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- qwen_tts/inference/qwen3_tts_model.py +2 -2
- {qwen_tts-0.0.4.dist-info → qwen_tts-0.0.5.dist-info}/METADATA +7 -8
- {qwen_tts-0.0.4.dist-info → qwen_tts-0.0.5.dist-info}/RECORD +7 -7
- {qwen_tts-0.0.4.dist-info → qwen_tts-0.0.5.dist-info}/WHEEL +0 -0
- {qwen_tts-0.0.4.dist-info → qwen_tts-0.0.5.dist-info}/entry_points.txt +0 -0
- {qwen_tts-0.0.4.dist-info → qwen_tts-0.0.5.dist-info}/licenses/LICENSE +0 -0
- {qwen_tts-0.0.4.dist-info → qwen_tts-0.0.5.dist-info}/top_level.txt +0 -0
|
@@ -639,7 +639,7 @@ class Qwen3TTSModel:
|
|
|
639
639
|
text: Union[str, List[str]],
|
|
640
640
|
instruct: Union[str, List[str]],
|
|
641
641
|
language: Union[str, List[str]] = None,
|
|
642
|
-
non_streaming_mode: bool =
|
|
642
|
+
non_streaming_mode: bool = True,
|
|
643
643
|
**kwargs,
|
|
644
644
|
) -> Tuple[List[np.ndarray], int]:
|
|
645
645
|
"""
|
|
@@ -735,7 +735,7 @@ class Qwen3TTSModel:
|
|
|
735
735
|
speaker: Union[str, List[str]],
|
|
736
736
|
language: Union[str, List[str]] = None,
|
|
737
737
|
instruct: Optional[Union[str, List[str]]] = None,
|
|
738
|
-
non_streaming_mode: bool =
|
|
738
|
+
non_streaming_mode: bool = True,
|
|
739
739
|
**kwargs,
|
|
740
740
|
) -> Tuple[List[np.ndarray], int]:
|
|
741
741
|
"""
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: qwen-tts
|
|
3
|
-
Version: 0.0.
|
|
3
|
+
Version: 0.0.5
|
|
4
4
|
Summary: Qwen-TTS python package
|
|
5
5
|
Author: Alibaba Qwen Team
|
|
6
6
|
License: Apache-2.0
|
|
@@ -35,7 +35,7 @@ Dynamic: license-file
|
|
|
35
35
|
<p>
|
|
36
36
|
|
|
37
37
|
<p align="center">
|
|
38
|
-
  🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS">ModelScope</a>   |   📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115">Blog</a>   |   📑 <a href="https://
|
|
38
|
+
  🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS">ModelScope</a>   |   📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115">Blog</a>   |   📑 <a href="https://arxiv.org/abs/2601.15621">Paper</a>  
|
|
39
39
|
<br>
|
|
40
40
|
🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen3-TTS">Hugging Face Demo</a>   |    🖥️ <a href="https://modelscope.cn/studios/Qwen/Qwen3-TTS">ModelScope Demo</a>   |   💬 <a href="https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png">WeChat (微信)</a>   |   🫨 <a href="https://discord.gg/CV4E9rpNSD">Discord</a>   |   📑 <a href="https://help.aliyun.com/zh/model-studio/qwen-tts-realtime">API</a>
|
|
41
41
|
|
|
@@ -66,7 +66,7 @@ We release **Qwen3-TTS**, a series of powerful speech generation capabilities de
|
|
|
66
66
|
- [vLLM Usage](#vllm-usage)
|
|
67
67
|
- [Fine Tuning](#fine-tuning)
|
|
68
68
|
- [Evaluation](#evaluation)
|
|
69
|
-
|
|
69
|
+
- [Citation](#citation)
|
|
70
70
|
|
|
71
71
|
## Overview
|
|
72
72
|
### Introduction
|
|
@@ -1367,18 +1367,17 @@ During evaluation, we ran inference for all models with `dtype=torch.bfloat16` a
|
|
|
1367
1367
|
</details>
|
|
1368
1368
|
|
|
1369
1369
|
|
|
1370
|
-
|
|
1370
|
+
## Citation
|
|
1371
1371
|
|
|
1372
1372
|
If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil: :)
|
|
1373
1373
|
|
|
1374
|
-
|
|
1375
1374
|
```BibTeX
|
|
1376
1375
|
@article{Qwen3-TTS,
|
|
1377
1376
|
title={Qwen3-TTS Technical Report},
|
|
1378
|
-
author={},
|
|
1379
|
-
journal={arXiv preprint arXiv:},
|
|
1377
|
+
author={Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
|
|
1378
|
+
journal={arXiv preprint arXiv:2601.15621},
|
|
1380
1379
|
year={2026}
|
|
1381
1380
|
}
|
|
1382
|
-
```
|
|
1381
|
+
```
|
|
1383
1382
|
|
|
1384
1383
|
<br>
|
|
@@ -14,11 +14,11 @@ qwen_tts/core/tokenizer_25hz/vq/core_vq.py,sha256=01-p8A70hjNhST4QL04o8JJIhJcRff
|
|
|
14
14
|
qwen_tts/core/tokenizer_25hz/vq/speech_vq.py,sha256=fGj8uoxQjYoY4iQbVjMC0b9G-OyxUVxZIiJj2FJLspg,14833
|
|
15
15
|
qwen_tts/core/tokenizer_25hz/vq/whisper_encoder.py,sha256=oXSLNJaLqO_-v5AsSkOZlBs-Sbyj9sASD8Zz47p9dn0,14351
|
|
16
16
|
qwen_tts/core/tokenizer_25hz/vq/assets/mel_filters.npz,sha256=dFCucHI6XvnTQePO5ijHywF382zkLES37SvzMl8PbUw,4271
|
|
17
|
-
qwen_tts/inference/qwen3_tts_model.py,sha256=
|
|
17
|
+
qwen_tts/inference/qwen3_tts_model.py,sha256=4dpFBzKFfB9f4-NuurhdsvbcakjKr_aXP0YzhOMCdeQ,37121
|
|
18
18
|
qwen_tts/inference/qwen3_tts_tokenizer.py,sha256=vX1-6_rJIGQ7QtKd932ngHJYvEBjBUSos1tCEtOyFaw,15698
|
|
19
|
-
qwen_tts-0.0.
|
|
20
|
-
qwen_tts-0.0.
|
|
21
|
-
qwen_tts-0.0.
|
|
22
|
-
qwen_tts-0.0.
|
|
23
|
-
qwen_tts-0.0.
|
|
24
|
-
qwen_tts-0.0.
|
|
19
|
+
qwen_tts-0.0.5.dist-info/licenses/LICENSE,sha256=pEpggcc6118CVbsrtcq3TvGClWWolaJOU6TxEpCrdlU,11343
|
|
20
|
+
qwen_tts-0.0.5.dist-info/METADATA,sha256=UOYyVhBHbYvtuIV2b4hnb26s9h_ujp3zi-bFPcHzcrY,61233
|
|
21
|
+
qwen_tts-0.0.5.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
|
|
22
|
+
qwen_tts-0.0.5.dist-info/entry_points.txt,sha256=hcoVetKUabLdCmu2ST4jGo8jilnoslpFzV-bxlHf0E0,57
|
|
23
|
+
qwen_tts-0.0.5.dist-info/top_level.txt,sha256=1o-44WiYkUtYVTiL9eexzyNQXK6YWCOGZltO81PUirA,9
|
|
24
|
+
qwen_tts-0.0.5.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|