qwen-tts 0.0.4__tar.gz → 0.0.5__tar.gz

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.
Files changed (25) hide show
  1. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/PKG-INFO +7 -8
  2. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/README.md +6 -7
  3. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/pyproject.toml +1 -1
  4. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/inference/qwen3_tts_model.py +2 -2
  5. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/LICENSE +0 -0
  6. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/MANIFEST.in +0 -0
  7. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/__init__.py +0 -0
  8. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/__main__.py +0 -0
  9. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/cli/demo.py +0 -0
  10. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/__init__.py +0 -0
  11. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/models/__init__.py +0 -0
  12. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/models/configuration_qwen3_tts.py +0 -0
  13. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/models/modeling_qwen3_tts.py +0 -0
  14. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/models/processing_qwen3_tts.py +0 -0
  15. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_12hz/configuration_qwen3_tts_tokenizer_v2.py +0 -0
  16. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_12hz/modeling_qwen3_tts_tokenizer_v2.py +0 -0
  17. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_25hz/configuration_qwen3_tts_tokenizer_v1.py +0 -0
  18. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_25hz/modeling_qwen3_tts_tokenizer_v1.py +0 -0
  19. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_25hz/vq/assets/mel_filters.npz +0 -0
  20. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_25hz/vq/core_vq.py +0 -0
  21. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_25hz/vq/speech_vq.py +0 -0
  22. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/core/tokenizer_25hz/vq/whisper_encoder.py +0 -0
  23. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/inference/qwen3_tts_tokenizer.py +0 -0
  24. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts.egg-info/SOURCES.txt +0 -0
  25. {qwen_tts-0.0.4 → qwen_tts-0.0.5}/setup.cfg +0 -0
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: qwen-tts
3
- Version: 0.0.4
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
- &nbsp&nbsp🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115">Blog</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://github.com/QwenLM/Qwen3-TTS/blob/main/assets/Qwen3_TTS.pdf">Paper</a>&nbsp&nbsp
38
+ &nbsp&nbsp🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115">Blog</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://arxiv.org/abs/2601.15621">Paper</a>&nbsp&nbsp
39
39
  <br>
40
40
  🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen3-TTS">Hugging Face Demo</a>&nbsp&nbsp | &nbsp&nbsp 🖥️ <a href="https://modelscope.cn/studios/Qwen/Qwen3-TTS">ModelScope Demo</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href="https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href="https://discord.gg/CV4E9rpNSD">Discord</a>&nbsp&nbsp | &nbsp&nbsp📑 <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
- <!-- - [Citation](#citation) -->
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
- <!-- ## Citation
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>
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/README.md RENAMED
@@ -7,7 +7,7 @@
7
7
  <p>
8
8
 
9
9
  <p align="center">
10
- &nbsp&nbsp🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115">Blog</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://github.com/QwenLM/Qwen3-TTS/blob/main/assets/Qwen3_TTS.pdf">Paper</a>&nbsp&nbsp
10
+ &nbsp&nbsp🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115">Blog</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://arxiv.org/abs/2601.15621">Paper</a>&nbsp&nbsp
11
11
  <br>
12
12
  🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen3-TTS">Hugging Face Demo</a>&nbsp&nbsp | &nbsp&nbsp 🖥️ <a href="https://modelscope.cn/studios/Qwen/Qwen3-TTS">ModelScope Demo</a>&nbsp&nbsp | &nbsp&nbsp💬 <a href="https://github.com/QwenLM/Qwen/blob/main/assets/wechat.png">WeChat (微信)</a>&nbsp&nbsp | &nbsp&nbsp🫨 <a href="https://discord.gg/CV4E9rpNSD">Discord</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://help.aliyun.com/zh/model-studio/qwen-tts-realtime">API</a>
13
13
 
@@ -38,7 +38,7 @@ We release **Qwen3-TTS**, a series of powerful speech generation capabilities de
38
38
  - [vLLM Usage](#vllm-usage)
39
39
  - [Fine Tuning](#fine-tuning)
40
40
  - [Evaluation](#evaluation)
41
- <!-- - [Citation](#citation) -->
41
+ - [Citation](#citation)
42
42
 
43
43
  ## Overview
44
44
  ### Introduction
@@ -1339,18 +1339,17 @@ During evaluation, we ran inference for all models with `dtype=torch.bfloat16` a
1339
1339
  </details>
1340
1340
 
1341
1341
 
1342
- <!-- ## Citation
1342
+ ## Citation
1343
1343
 
1344
1344
  If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil: :)
1345
1345
 
1346
-
1347
1346
  ```BibTeX
1348
1347
  @article{Qwen3-TTS,
1349
1348
  title={Qwen3-TTS Technical Report},
1350
- author={},
1351
- journal={arXiv preprint arXiv:},
1349
+ 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},
1350
+ journal={arXiv preprint arXiv:2601.15621},
1352
1351
  year={2026}
1353
1352
  }
1354
- ``` -->
1353
+ ```
1355
1354
 
1356
1355
  <br>
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/pyproject.toml RENAMED
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "qwen-tts"
7
- version = "0.0.4"
7
+ version = "0.0.5"
8
8
  description = "Qwen-TTS python package"
9
9
  readme = "README.md"
10
10
  requires-python = ">=3.9"
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/inference/qwen3_tts_model.py RENAMED
@@ -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 = False,
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 = False,
738
+ non_streaming_mode: bool = True,
739
739
  **kwargs,
740
740
  ) -> Tuple[List[np.ndarray], int]:
741
741
  """
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/LICENSE RENAMED
File without changes
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/MANIFEST.in RENAMED
File without changes
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/__init__.py RENAMED
File without changes
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/__main__.py RENAMED
File without changes
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/qwen_tts/cli/demo.py RENAMED
File without changes
{qwen_tts-0.0.4 → qwen_tts-0.0.5}/setup.cfg RENAMED
File without changes