indextts2-inference 2.0.1__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 (89) hide show
  1. indextts2_inference-2.0.1/.gitattributes +15 -0
  2. indextts2_inference-2.0.1/.github/workflows/ci.yml +29 -0
  3. indextts2_inference-2.0.1/.github/workflows/release-please.yml +17 -0
  4. indextts2_inference-2.0.1/.github/workflows/release.yml +20 -0
  5. indextts2_inference-2.0.1/.gitignore +44 -0
  6. indextts2_inference-2.0.1/.python-version +1 -0
  7. indextts2_inference-2.0.1/.release-please-manifest.json +3 -0
  8. indextts2_inference-2.0.1/CHANGELOG.md +181 -0
  9. indextts2_inference-2.0.1/DISCLAIMER +43 -0
  10. indextts2_inference-2.0.1/LICENSE +57 -0
  11. indextts2_inference-2.0.1/LICENSE_ZH.txt +52 -0
  12. indextts2_inference-2.0.1/PKG-INFO +45 -0
  13. indextts2_inference-2.0.1/README.md +170 -0
  14. indextts2_inference-2.0.1/checkpoints/config.yaml +120 -0
  15. indextts2_inference-2.0.1/indextts/__init__.py +4 -0
  16. indextts2_inference-2.0.1/indextts/accel/__init__.py +9 -0
  17. indextts2_inference-2.0.1/indextts/accel/accel_engine.py +553 -0
  18. indextts2_inference-2.0.1/indextts/accel/attention.py +154 -0
  19. indextts2_inference-2.0.1/indextts/accel/gpt2_accel.py +181 -0
  20. indextts2_inference-2.0.1/indextts/accel/kv_manager.py +209 -0
  21. indextts2_inference-2.0.1/indextts/emotion.py +120 -0
  22. indextts2_inference-2.0.1/indextts/gpt/__init__.py +0 -0
  23. indextts2_inference-2.0.1/indextts/gpt/conformer/__init__.py +0 -0
  24. indextts2_inference-2.0.1/indextts/gpt/conformer/attention.py +312 -0
  25. indextts2_inference-2.0.1/indextts/gpt/conformer/embedding.py +163 -0
  26. indextts2_inference-2.0.1/indextts/gpt/conformer/subsampling.py +348 -0
  27. indextts2_inference-2.0.1/indextts/gpt/conformer_encoder.py +520 -0
  28. indextts2_inference-2.0.1/indextts/gpt/model_v2.py +862 -0
  29. indextts2_inference-2.0.1/indextts/gpt/perceiver.py +267 -0
  30. indextts2_inference-2.0.1/indextts/infer_v2.py +802 -0
  31. indextts2_inference-2.0.1/indextts/logging.py +13 -0
  32. indextts2_inference-2.0.1/indextts/s2mel/dac/__init__.py +5 -0
  33. indextts2_inference-2.0.1/indextts/s2mel/dac/nn/__init__.py +2 -0
  34. indextts2_inference-2.0.1/indextts/s2mel/dac/nn/layers.py +33 -0
  35. indextts2_inference-2.0.1/indextts/s2mel/dac/nn/quantize.py +334 -0
  36. indextts2_inference-2.0.1/indextts/s2mel/modules/audio.py +77 -0
  37. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/activations.py +120 -0
  38. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/__init__.py +0 -0
  39. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/activation1d.py +77 -0
  40. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/anti_alias_activation.cpp +23 -0
  41. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/anti_alias_activation_cuda.cu +246 -0
  42. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/compat.h +29 -0
  43. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/load.py +96 -0
  44. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/type_shim.h +92 -0
  45. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/torch/__init__.py +6 -0
  46. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/torch/act.py +30 -0
  47. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/torch/filter.py +101 -0
  48. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/alias_free_activation/torch/resample.py +58 -0
  49. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/bigvgan.py +450 -0
  50. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/config.json +63 -0
  51. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/env.py +18 -0
  52. indextts2_inference-2.0.1/indextts/s2mel/modules/bigvgan/utils.py +69 -0
  53. indextts2_inference-2.0.1/indextts/s2mel/modules/campplus/DTDNN.py +115 -0
  54. indextts2_inference-2.0.1/indextts/s2mel/modules/campplus/layers.py +253 -0
  55. indextts2_inference-2.0.1/indextts/s2mel/modules/commons.py +630 -0
  56. indextts2_inference-2.0.1/indextts/s2mel/modules/diffusion_transformer.py +257 -0
  57. indextts2_inference-2.0.1/indextts/s2mel/modules/encodec.py +292 -0
  58. indextts2_inference-2.0.1/indextts/s2mel/modules/flow_matching.py +186 -0
  59. indextts2_inference-2.0.1/indextts/s2mel/modules/gpt_fast/model.py +360 -0
  60. indextts2_inference-2.0.1/indextts/s2mel/modules/length_regulator.py +141 -0
  61. indextts2_inference-2.0.1/indextts/s2mel/modules/wavenet.py +174 -0
  62. indextts2_inference-2.0.1/indextts/utils/__init__.py +0 -0
  63. indextts2_inference-2.0.1/indextts/utils/arch_util.py +126 -0
  64. indextts2_inference-2.0.1/indextts/utils/checkpoint.py +31 -0
  65. indextts2_inference-2.0.1/indextts/utils/common.py +123 -0
  66. indextts2_inference-2.0.1/indextts/utils/front.py +660 -0
  67. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/amphion_codec/codec.py +427 -0
  68. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/amphion_codec/quantize/__init__.py +11 -0
  69. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/amphion_codec/quantize/factorized_vector_quantize.py +150 -0
  70. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/amphion_codec/quantize/lookup_free_quantize.py +77 -0
  71. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/amphion_codec/quantize/residual_vq.py +177 -0
  72. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/amphion_codec/quantize/vector_quantize.py +401 -0
  73. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/amphion_codec/vocos.py +881 -0
  74. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/kmeans/repcodec_model.py +201 -0
  75. indextts2_inference-2.0.1/indextts/utils/maskgct/models/codec/kmeans/vocos.py +850 -0
  76. indextts2_inference-2.0.1/indextts/utils/maskgct/models/tts/maskgct/ckpt/wav2vec2bert_stats.pt +0 -0
  77. indextts2_inference-2.0.1/indextts/utils/maskgct/models/tts/maskgct/llama_nar.py +650 -0
  78. indextts2_inference-2.0.1/indextts/utils/maskgct/models/tts/maskgct/maskgct_s2a.py +501 -0
  79. indextts2_inference-2.0.1/indextts/utils/maskgct_utils.py +259 -0
  80. indextts2_inference-2.0.1/indextts/utils/typical_sampling.py +31 -0
  81. indextts2_inference-2.0.1/indextts/utils/xtransformers.py +1260 -0
  82. indextts2_inference-2.0.1/pyproject.toml +87 -0
  83. indextts2_inference-2.0.1/release-please-config.json +10 -0
  84. indextts2_inference-2.0.1/tests/__init__.py +0 -0
  85. indextts2_inference-2.0.1/tests/test_common.py +102 -0
  86. indextts2_inference-2.0.1/tests/test_emotion.py +100 -0
  87. indextts2_inference-2.0.1/tests/test_front.py +240 -0
  88. indextts2_inference-2.0.1/tests/test_typical_sampling.py +41 -0
  89. indextts2_inference-2.0.1/uv.lock +3334 -0
@@ -0,0 +1,15 @@
1
+ examples/voice_02.wav filter=lfs diff=lfs merge=lfs -text
2
+ examples/voice_04.wav filter=lfs diff=lfs merge=lfs -text
3
+ examples/emo_sad.wav filter=lfs diff=lfs merge=lfs -text
4
+ examples/voice_03.wav filter=lfs diff=lfs merge=lfs -text
5
+ examples/voice_06.wav filter=lfs diff=lfs merge=lfs -text
6
+ examples/voice_08.wav filter=lfs diff=lfs merge=lfs -text
7
+ tests/sample_prompt.wav filter=lfs diff=lfs merge=lfs -text
8
+ examples/emo_hate.wav filter=lfs diff=lfs merge=lfs -text
9
+ examples/voice_01.wav filter=lfs diff=lfs merge=lfs -text
10
+ examples/voice_05.wav filter=lfs diff=lfs merge=lfs -text
11
+ examples/voice_09.wav filter=lfs diff=lfs merge=lfs -text
12
+ examples/voice_10.wav filter=lfs diff=lfs merge=lfs -text
13
+ examples/voice_12.wav filter=lfs diff=lfs merge=lfs -text
14
+ examples/voice_07.wav filter=lfs diff=lfs merge=lfs -text
15
+ examples/voice_11.wav filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,29 @@
1
+ name: CI
2
+
3
+ on:
4
+ push:
5
+ branches: [main]
6
+ pull_request:
7
+
8
+ jobs:
9
+ lint:
10
+ runs-on: ubuntu-latest
11
+ steps:
12
+ - uses: actions/checkout@v4
13
+
14
+ - uses: astral-sh/setup-uv@v6
15
+
16
+ - run: uv run --group dev ruff check
17
+
18
+ test:
19
+ runs-on: ubuntu-latest
20
+ steps:
21
+ - uses: actions/checkout@v4
22
+
23
+ - uses: astral-sh/setup-uv@v6
24
+
25
+ - run: uv run --group test pytest --cov=indextts --cov-report=xml
26
+
27
+ - uses: codecov/codecov-action@v5
28
+ with:
29
+ token: ${{ secrets.CODECOV_TOKEN }}
@@ -0,0 +1,17 @@
1
+ name: Release Please
2
+
3
+ on:
4
+ push:
5
+ branches: [main]
6
+
7
+ permissions:
8
+ contents: write
9
+ pull-requests: write
10
+
11
+ jobs:
12
+ release-please:
13
+ runs-on: ubuntu-latest
14
+ steps:
15
+ - uses: googleapis/release-please-action@v4
16
+ with:
17
+ token: ${{ secrets.RELEASE_PLEASE_TOKEN }}
@@ -0,0 +1,20 @@
1
+ name: Release
2
+
3
+ on:
4
+ push:
5
+ tags: ["v*"]
6
+
7
+ jobs:
8
+ publish:
9
+ runs-on: ubuntu-latest
10
+ environment: pypi
11
+ permissions:
12
+ id-token: write
13
+ steps:
14
+ - uses: actions/checkout@v4
15
+
16
+ - uses: astral-sh/setup-uv@v6
17
+
18
+ - run: uv build
19
+
20
+ - uses: pypa/gh-action-pypi-publish@release/v1
@@ -0,0 +1,44 @@
1
+ # Development Tools.
2
+ .mypy_cache/
3
+ .ruff_cache/
4
+ __pycache__/
5
+ .idea/
6
+ .vscode/
7
+
8
+ # Environments.
9
+ .venv*/
10
+ venv*/
11
+ conda_env*/
12
+
13
+ # Python Bytecode.
14
+ *.py[cod]
15
+
16
+ # Distribution/Packaging.
17
+ /build/
18
+ /dist/
19
+ *.egg-info/
20
+ .pypirc
21
+
22
+ # Operating System Junk.
23
+ *.DS_Store
24
+ Thumbs.db
25
+ desktop.ini
26
+
27
+ # IndexTTS.
28
+ /cache/
29
+ /checkpoints/*
30
+ !/checkpoints/*.yaml
31
+ /outputs/
32
+
33
+ # Test outputs.
34
+ test_*.wav
35
+ .coverage
36
+ htmlcov/
37
+ .pytest_cache/
38
+
39
+ # CUDA kernel build artifacts.
40
+ indextts/s2mel/modules/bigvgan/alias_free_activation/cuda/build/
41
+
42
+ # NeMo cache.
43
+ indextts/utils/nemo_es_cache/
44
+ indextts/utils/tagger_cache/
@@ -0,0 +1 @@
1
+ 3.14
@@ -0,0 +1,3 @@
1
+ {
2
+ ".": "2.0.1"
3
+ }
@@ -0,0 +1,181 @@
1
+ # Changelog
2
+
3
+ ## [2.0.1](https://github.com/nicokim/indextts2-inference/compare/v2.0.0...v2.0.1) (2026-02-26)
4
+
5
+
6
+ ### Bug Fixes
7
+
8
+ * match PyPI project name (indextts2-inference) ([#6](https://github.com/nicokim/indextts2-inference/issues/6)) ([e6f033c](https://github.com/nicokim/indextts2-inference/commit/e6f033c826dd3a2dba923c00957b6bc68ab53a5c))
9
+
10
+ ## [2.0.0](https://github.com/nicokim/indextts2-inference/compare/v1.0.0...v2.0.0) (2026-02-26)
11
+
12
+
13
+ ### ⚠ BREAKING CHANGES
14
+
15
+ * de-vendor transformers, support transformers 5.x ([#2](https://github.com/nicokim/indextts2-inference/issues/2))
16
+ * **webui:** Easier DeepSpeed launch argument
17
+
18
+ ### Features
19
+
20
+ * **accel:** add batch support ([44b5ffc](https://github.com/nicokim/indextts2-inference/commit/44b5ffcb5dda05217e08521d58a919a44c6dac2b))
21
+ * achieve inference acceleration for the gpt2 stage ([c1ef414](https://github.com/nicokim/indextts2-inference/commit/c1ef4148af34dcb1943ae1fe4bded0f7602f68bb))
22
+ * achieve inference acceleration for the gpt2 stage (3.79×) ([1d5d079](https://github.com/nicokim/indextts2-inference/commit/1d5d079aaa290a7179967e80b7e25f5aa002cd8f))
23
+ * achieve inference acceleration for the s2mel stage (1.61×) ([e42480c](https://github.com/nicokim/indextts2-inference/commit/e42480ced8af8bf8ef596b2420faa5c86fa64ed2))
24
+ * add batch support ([3c36027](https://github.com/nicokim/indextts2-inference/commit/3c360273da9738158ee72bf6d47710033f835049))
25
+ * Add reusable Emotion Vector normalization helper ([8aa8064](https://github.com/nicokim/indextts2-inference/commit/8aa8064a53c5b5b53ff20f6de94aaadc18a4cd9d))
26
+ * **cli:** Support XPU ([#322](https://github.com/nicokim/indextts2-inference/issues/322)) ([e83df4e](https://github.com/nicokim/indextts2-inference/commit/e83df4e4270e6b1f5f08b341907689c078a382c4))
27
+ * de-vendor transformers, support transformers 5.x ([#2](https://github.com/nicokim/indextts2-inference/issues/2)) ([ad522fe](https://github.com/nicokim/indextts2-inference/commit/ad522fe80dad9aefd87ce7c233d02b17f6e11733))
28
+ * DeepSpeed is now an optional dependency which can be disabled ([936e6ac](https://github.com/nicokim/indextts2-inference/commit/936e6ac4dd4558b29c431e709c57a04cbd9c78bc))
29
+ * Extend GPU Check utility to support more GPUs ([39a035d](https://github.com/nicokim/indextts2-inference/commit/39a035d1066dee3baeb45a5580555ea2013591f0))
30
+ * **front.py:** add regex pattern for technical terms ([82a5b90](https://github.com/nicokim/indextts2-inference/commit/82a5b9004a90bb6a9656cfb95e3aaa05d1117a0a))
31
+ * gumbel_softmax_sampler ([a3b884f](https://github.com/nicokim/indextts2-inference/commit/a3b884ff6ff401923e6242fb87630be0a6d0f221))
32
+ * **i18n:** Add missing UI translation strings ([5f0b0a9](https://github.com/nicokim/indextts2-inference/commit/5f0b0a9f9c57c05440d6d3992e90792d70023ae5))
33
+ * Implement `emo_alpha` scaling of emotion vectors and emotion text ([9668064](https://github.com/nicokim/indextts2-inference/commit/9668064377fcba7d3e8643c8680d5f8d37ddb2a9))
34
+ * **indextts:** add glossary support for custom term pronunciations ([6deed97](https://github.com/nicokim/indextts2-inference/commit/6deed97efe636bf68825ebb0ec82ec994fd1d42f))
35
+ * optimize s2mel stage ([31e7e85](https://github.com/nicokim/indextts2-inference/commit/31e7e855e21779c5ad0cd6b7b0ae4329c0c91ec2))
36
+ * **sampler:** enhance with greedy sampling mode ([42a7339](https://github.com/nicokim/indextts2-inference/commit/42a73394e9f9049699bc8e5210a705249e248b3f))
37
+ * Warn if input text contains UNK tokens ([34be9bf](https://github.com/nicokim/indextts2-inference/commit/34be9bfb146ed4cf41808f002fc47332ddddaebd))
38
+ * **webui.py:** add glossary term validation and error handling ([a7099c4](https://github.com/nicokim/indextts2-inference/commit/a7099c4a6e13a59b2b4e9c8e90e06b61595412f0))
39
+ * **webui:** Easier DeepSpeed launch argument ([f0badb1](https://github.com/nicokim/indextts2-inference/commit/f0badb13af7f84f92caa4d7d65b56ef4e3456337))
40
+ * **webui:** Implement emotion weighting for vectors and text modes ([d899770](https://github.com/nicokim/indextts2-inference/commit/d8997703137434e2d71329721e52e88eff534572))
41
+ * **webui:** Implement speech synthesis progress bar ([555e146](https://github.com/nicokim/indextts2-inference/commit/555e146fb4066d465225a850b21243e5b7eccd0e))
42
+ * 归一化参数到推荐的范围,改善用户体验 ([48a71af](https://github.com/nicokim/indextts2-inference/commit/48a71aff6da497c3d14c9a0bd2be9d627c8c45d3))
43
+ * 归一化参数到推荐的范围,改善用户体验 ([af2b06e](https://github.com/nicokim/indextts2-inference/commit/af2b06e061937d291e276a0aa1bd4a2254a06078))
44
+ * 裁剪过长的输入音频至15s,减少爆内存和显存 ([009428b](https://github.com/nicokim/indextts2-inference/commit/009428b62dc60b9d7bfdddd1641d51df9c2afa80))
45
+ * 裁剪过长的输入音频至15s,减少爆内存和显存 ([0828dcb](https://github.com/nicokim/indextts2-inference/commit/0828dcb098247760ba17ba5ad8a5b6b5cb460f95))
46
+
47
+
48
+ ### Bug Fixes
49
+
50
+ * add force_rebuild flag for fused alias_free_activation and update installation instructions ([59c05c0](https://github.com/nicokim/indextts2-inference/commit/59c05c0765b61f4c8fe5d66ff7fe3c6a960e09e4))
51
+ * Add support for melancholic emotion in text-to-emotion vectors ([a6a955d](https://github.com/nicokim/indextts2-inference/commit/a6a955d2aa18d6400b2f4cdaad35e792d5bb231b))
52
+ * **cli:** More robust device priority checks ([6113567](https://github.com/nicokim/indextts2-inference/commit/6113567e94a885193f451d3d81665a609e9efbe5))
53
+ * Don't load DeepSpeed if use_deepspeed is False ([05a8ae4](https://github.com/nicokim/indextts2-inference/commit/05a8ae45e5da8ab7bdb035069181c11dfa3ac2bf))
54
+ * Empty generator -> IndexError problem on non-streaming infer() ([db5b39b](https://github.com/nicokim/indextts2-inference/commit/db5b39bb6ad903c219b2dd33d60b0f0bdaede664))
55
+ * Empty generator -> IndexError problem on non-streaming infer() ([750d9d9](https://github.com/nicokim/indextts2-inference/commit/750d9d9d15c90cfbf2d1f386a481e0087a834a61))
56
+ * Fast and robust text-to-emotion algorithm ([58ad225](https://github.com/nicokim/indextts2-inference/commit/58ad225fb41c99ebf873f3b1694391f8164ac0d3))
57
+ * Fix character encoding in examples ([55b7d32](https://github.com/nicokim/indextts2-inference/commit/55b7d321495b530c5467ecdf0e06fb996a011a71))
58
+ * Fix internal text-to-emotion vector labels ([feba501](https://github.com/nicokim/indextts2-inference/commit/feba5010137460ec8decaba2603da7819cb963e6))
59
+ * **front.py:** load full term glossary entries from yaml file ([1460adb](https://github.com/nicokim/indextts2-inference/commit/1460adbdc54d13af39b155e2760d0045ac23a825))
60
+ * handle multiple sentence placeholders in de_tokenized_by_CJK_char ([267e344](https://github.com/nicokim/indextts2-inference/commit/267e344a0956c09f4c2ff9e16d1c6bda7d67c11a))
61
+ * Improve .gitignore and re-add config file ([5ffb84b](https://github.com/nicokim/indextts2-inference/commit/5ffb84b427d2d7e8fa597cc4f5e31c2b30cfd492))
62
+ * **infer_v2:** Correct the import path of BigVGAN's custom cuda kernel ([e409c4a](https://github.com/nicokim/indextts2-inference/commit/e409c4a19b911f203de69f043987e9f37d78b0c8))
63
+ * Suppress pandas PyArrow future dependency warning ([d5cdb5e](https://github.com/nicokim/indextts2-inference/commit/d5cdb5eb3cfb34cbb901e4da4a0302c07e6a5e06))
64
+ * Update pandas to fix Gradio errors ([3e64c4a](https://github.com/nicokim/indextts2-inference/commit/3e64c4ac11c12d119567fa3a1b47da577170fbc8))
65
+ * update PINYIN_TONE_PATTERN and NormalizerZh ([7d943b3](https://github.com/nicokim/indextts2-inference/commit/7d943b362dbc950edc2dfc1fb7726dbfd5d39b81))
66
+ * use simple version tags (v*) for release-please ([#4](https://github.com/nicokim/indextts2-inference/issues/4)) ([76c70aa](https://github.com/nicokim/indextts2-inference/commit/76c70aa035a42013473cf5ad39328dba77cbcf7d))
67
+ * Use WeTextProcessing on Linux, and wetext on other platforms ([dcdb061](https://github.com/nicokim/indextts2-inference/commit/dcdb0614bf7fc29fe560969324478c29928b1695))
68
+ * **webui.py:** replace return statements with warnings and update markdown table ([fa7962f](https://github.com/nicokim/indextts2-inference/commit/fa7962f1f2decd7a430d2d62544d2e3a3e596d06))
69
+ * **webui.py:** strip tailing whitespace for glossary terms ([6b6606a](https://github.com/nicokim/indextts2-inference/commit/6b6606a2f4d1974ea8ae1413e609b7a17af882fc))
70
+ * **webui:** Add support for Gradio 5.45.0 and higher ([ef09710](https://github.com/nicokim/indextts2-inference/commit/ef097101b7ab70120250c9c3f6394174e656590e))
71
+ * **webui:** Experimental checkbox bugfixes and add visual warning label ([ec368de](https://github.com/nicokim/indextts2-inference/commit/ec368de9329c7beffa3df369005c7d25e7684980))
72
+ * **webui:** Fix unintentional empty spacing between control groups ([f041d8e](https://github.com/nicokim/indextts2-inference/commit/f041d8eb64e1af1f7a5def01247d564b1a283a5b))
73
+ * **webui:** Make the Advanced Settings visible by default again ([e185fa1](https://github.com/nicokim/indextts2-inference/commit/e185fa1ce748de6759f772f3852024c5443724f3))
74
+ * **webui:** Make the Emotion Control Weight slider visible again ([c5f9a31](https://github.com/nicokim/indextts2-inference/commit/c5f9a311275447707791c2758a2267dd137142f2))
75
+ * **webui:** New default emo_alpha recommendation instead of scaling ([1520d06](https://github.com/nicokim/indextts2-inference/commit/1520d0689baa4bacbf095e1c715417de555c123d))
76
+ * 中文readme标题显示问题 ([ce2f71a](https://github.com/nicokim/indextts2-inference/commit/ce2f71aae5b568c17428903aa3f8890c10fe4d26))
77
+ * 修复样本音频太长报错的问题,对音频进行裁切。 ([2cfc76a](https://github.com/nicokim/indextts2-inference/commit/2cfc76ad9c49b4376e3d10a5bfeafbad9e5b5cd3))
78
+ * 添加英语缩写处理 ([414f2a4](https://github.com/nicokim/indextts2-inference/commit/414f2a4052b49248a4ff99380bb84040d0c6e22a))
79
+ * 添加英语缩写处理 ([bb4d76a](https://github.com/nicokim/indextts2-inference/commit/bb4d76aa2a1b5e3efb00ccc6ee7fc45e453f2701))
80
+ * 避免在 MinGW-w64 环境 jit compile cuda ext ([92bb2eb](https://github.com/nicokim/indextts2-inference/commit/92bb2eb0c0a5242943fb86950ce68c73576053a4))
81
+
82
+
83
+ ### Documentation
84
+
85
+ * Add a stronger warning about unsupported installation methods ([6c76807](https://github.com/nicokim/indextts2-inference/commit/6c768073e9519fa253090d539779e2d31be03cf5))
86
+ * Add Alibaba's high-bandwidth PyPI mirror for China ([30848ef](https://github.com/nicokim/indextts2-inference/commit/30848efd45f91d55b7f79f7f4a9388c74077afd7))
87
+ * Add FP16 usage advice for faster inference ([d777b8a](https://github.com/nicokim/indextts2-inference/commit/d777b8a0290cced0064eb5f503a25b65b148c1bc))
88
+ * Add quick uv installation technique ([429c06c](https://github.com/nicokim/indextts2-inference/commit/429c06c787115b4036330181e392785aa9b971f9))
89
+ * Add usage note regarding random sampling ([c3d7ab4](https://github.com/nicokim/indextts2-inference/commit/c3d7ab4adce98e8f46edb1a31374f2f64d72f51c))
90
+ * Clarify that UV handles Python and the environment creation ([cc9c6b6](https://github.com/nicokim/indextts2-inference/commit/cc9c6b6cfe49c6d9e6f84247b785ac08a2c808f5))
91
+ * Document the DeepSpeed performance effects ([85ba55a](https://github.com/nicokim/indextts2-inference/commit/85ba55a1d3ac92006f898115600f2cfef4e34251))
92
+ * Document the new `emo_alpha` feature for text-to-emotion mode ([3b5b6bc](https://github.com/nicokim/indextts2-inference/commit/3b5b6bca85ad01955bf773686647c3983e737dd9))
93
+ * Install HuggingFace CLI with high-speed download feature ([5471d82](https://github.com/nicokim/indextts2-inference/commit/5471d8256fc7867772030b1c0c75fe633f49ea76))
94
+ * Remove redundant "python" command instruction ([242604d](https://github.com/nicokim/indextts2-inference/commit/242604d27e63fba64df00985eb365013e7019bbe))
95
+ * Remove redundant "python" command instruction ([3236fa4](https://github.com/nicokim/indextts2-inference/commit/3236fa496a1d3ed587feb2b24fc85877aea51554))
96
+
97
+ ## [1.0.0](https://github.com/nicokim/indextts2-inference/compare/index-tts-inference-v0.1.0...index-tts-inference-v1.0.0) (2026-02-26)
98
+
99
+
100
+ ### ⚠ BREAKING CHANGES
101
+
102
+ * de-vendor transformers, support transformers 5.x ([#2](https://github.com/nicokim/indextts2-inference/issues/2))
103
+ * **webui:** Easier DeepSpeed launch argument
104
+
105
+ ### Features
106
+
107
+ * **accel:** add batch support ([44b5ffc](https://github.com/nicokim/indextts2-inference/commit/44b5ffcb5dda05217e08521d58a919a44c6dac2b))
108
+ * achieve inference acceleration for the gpt2 stage ([c1ef414](https://github.com/nicokim/indextts2-inference/commit/c1ef4148af34dcb1943ae1fe4bded0f7602f68bb))
109
+ * achieve inference acceleration for the gpt2 stage (3.79×) ([1d5d079](https://github.com/nicokim/indextts2-inference/commit/1d5d079aaa290a7179967e80b7e25f5aa002cd8f))
110
+ * achieve inference acceleration for the s2mel stage (1.61×) ([e42480c](https://github.com/nicokim/indextts2-inference/commit/e42480ced8af8bf8ef596b2420faa5c86fa64ed2))
111
+ * add batch support ([3c36027](https://github.com/nicokim/indextts2-inference/commit/3c360273da9738158ee72bf6d47710033f835049))
112
+ * Add reusable Emotion Vector normalization helper ([8aa8064](https://github.com/nicokim/indextts2-inference/commit/8aa8064a53c5b5b53ff20f6de94aaadc18a4cd9d))
113
+ * **cli:** Support XPU ([#322](https://github.com/nicokim/indextts2-inference/issues/322)) ([e83df4e](https://github.com/nicokim/indextts2-inference/commit/e83df4e4270e6b1f5f08b341907689c078a382c4))
114
+ * de-vendor transformers, support transformers 5.x ([#2](https://github.com/nicokim/indextts2-inference/issues/2)) ([ad522fe](https://github.com/nicokim/indextts2-inference/commit/ad522fe80dad9aefd87ce7c233d02b17f6e11733))
115
+ * DeepSpeed is now an optional dependency which can be disabled ([936e6ac](https://github.com/nicokim/indextts2-inference/commit/936e6ac4dd4558b29c431e709c57a04cbd9c78bc))
116
+ * Extend GPU Check utility to support more GPUs ([39a035d](https://github.com/nicokim/indextts2-inference/commit/39a035d1066dee3baeb45a5580555ea2013591f0))
117
+ * **front.py:** add regex pattern for technical terms ([82a5b90](https://github.com/nicokim/indextts2-inference/commit/82a5b9004a90bb6a9656cfb95e3aaa05d1117a0a))
118
+ * gumbel_softmax_sampler ([a3b884f](https://github.com/nicokim/indextts2-inference/commit/a3b884ff6ff401923e6242fb87630be0a6d0f221))
119
+ * **i18n:** Add missing UI translation strings ([5f0b0a9](https://github.com/nicokim/indextts2-inference/commit/5f0b0a9f9c57c05440d6d3992e90792d70023ae5))
120
+ * Implement `emo_alpha` scaling of emotion vectors and emotion text ([9668064](https://github.com/nicokim/indextts2-inference/commit/9668064377fcba7d3e8643c8680d5f8d37ddb2a9))
121
+ * **indextts:** add glossary support for custom term pronunciations ([6deed97](https://github.com/nicokim/indextts2-inference/commit/6deed97efe636bf68825ebb0ec82ec994fd1d42f))
122
+ * optimize s2mel stage ([31e7e85](https://github.com/nicokim/indextts2-inference/commit/31e7e855e21779c5ad0cd6b7b0ae4329c0c91ec2))
123
+ * **sampler:** enhance with greedy sampling mode ([42a7339](https://github.com/nicokim/indextts2-inference/commit/42a73394e9f9049699bc8e5210a705249e248b3f))
124
+ * Warn if input text contains UNK tokens ([34be9bf](https://github.com/nicokim/indextts2-inference/commit/34be9bfb146ed4cf41808f002fc47332ddddaebd))
125
+ * **webui.py:** add glossary term validation and error handling ([a7099c4](https://github.com/nicokim/indextts2-inference/commit/a7099c4a6e13a59b2b4e9c8e90e06b61595412f0))
126
+ * **webui:** Easier DeepSpeed launch argument ([f0badb1](https://github.com/nicokim/indextts2-inference/commit/f0badb13af7f84f92caa4d7d65b56ef4e3456337))
127
+ * **webui:** Implement emotion weighting for vectors and text modes ([d899770](https://github.com/nicokim/indextts2-inference/commit/d8997703137434e2d71329721e52e88eff534572))
128
+ * **webui:** Implement speech synthesis progress bar ([555e146](https://github.com/nicokim/indextts2-inference/commit/555e146fb4066d465225a850b21243e5b7eccd0e))
129
+ * 归一化参数到推荐的范围,改善用户体验 ([48a71af](https://github.com/nicokim/indextts2-inference/commit/48a71aff6da497c3d14c9a0bd2be9d627c8c45d3))
130
+ * 归一化参数到推荐的范围,改善用户体验 ([af2b06e](https://github.com/nicokim/indextts2-inference/commit/af2b06e061937d291e276a0aa1bd4a2254a06078))
131
+ * 裁剪过长的输入音频至15s,减少爆内存和显存 ([009428b](https://github.com/nicokim/indextts2-inference/commit/009428b62dc60b9d7bfdddd1641d51df9c2afa80))
132
+ * 裁剪过长的输入音频至15s,减少爆内存和显存 ([0828dcb](https://github.com/nicokim/indextts2-inference/commit/0828dcb098247760ba17ba5ad8a5b6b5cb460f95))
133
+
134
+
135
+ ### Bug Fixes
136
+
137
+ * add force_rebuild flag for fused alias_free_activation and update installation instructions ([59c05c0](https://github.com/nicokim/indextts2-inference/commit/59c05c0765b61f4c8fe5d66ff7fe3c6a960e09e4))
138
+ * Add support for melancholic emotion in text-to-emotion vectors ([a6a955d](https://github.com/nicokim/indextts2-inference/commit/a6a955d2aa18d6400b2f4cdaad35e792d5bb231b))
139
+ * **cli:** More robust device priority checks ([6113567](https://github.com/nicokim/indextts2-inference/commit/6113567e94a885193f451d3d81665a609e9efbe5))
140
+ * Don't load DeepSpeed if use_deepspeed is False ([05a8ae4](https://github.com/nicokim/indextts2-inference/commit/05a8ae45e5da8ab7bdb035069181c11dfa3ac2bf))
141
+ * Empty generator -> IndexError problem on non-streaming infer() ([db5b39b](https://github.com/nicokim/indextts2-inference/commit/db5b39bb6ad903c219b2dd33d60b0f0bdaede664))
142
+ * Empty generator -> IndexError problem on non-streaming infer() ([750d9d9](https://github.com/nicokim/indextts2-inference/commit/750d9d9d15c90cfbf2d1f386a481e0087a834a61))
143
+ * Fast and robust text-to-emotion algorithm ([58ad225](https://github.com/nicokim/indextts2-inference/commit/58ad225fb41c99ebf873f3b1694391f8164ac0d3))
144
+ * Fix character encoding in examples ([55b7d32](https://github.com/nicokim/indextts2-inference/commit/55b7d321495b530c5467ecdf0e06fb996a011a71))
145
+ * Fix internal text-to-emotion vector labels ([feba501](https://github.com/nicokim/indextts2-inference/commit/feba5010137460ec8decaba2603da7819cb963e6))
146
+ * **front.py:** load full term glossary entries from yaml file ([1460adb](https://github.com/nicokim/indextts2-inference/commit/1460adbdc54d13af39b155e2760d0045ac23a825))
147
+ * handle multiple sentence placeholders in de_tokenized_by_CJK_char ([267e344](https://github.com/nicokim/indextts2-inference/commit/267e344a0956c09f4c2ff9e16d1c6bda7d67c11a))
148
+ * Improve .gitignore and re-add config file ([5ffb84b](https://github.com/nicokim/indextts2-inference/commit/5ffb84b427d2d7e8fa597cc4f5e31c2b30cfd492))
149
+ * **infer_v2:** Correct the import path of BigVGAN's custom cuda kernel ([e409c4a](https://github.com/nicokim/indextts2-inference/commit/e409c4a19b911f203de69f043987e9f37d78b0c8))
150
+ * Suppress pandas PyArrow future dependency warning ([d5cdb5e](https://github.com/nicokim/indextts2-inference/commit/d5cdb5eb3cfb34cbb901e4da4a0302c07e6a5e06))
151
+ * Update pandas to fix Gradio errors ([3e64c4a](https://github.com/nicokim/indextts2-inference/commit/3e64c4ac11c12d119567fa3a1b47da577170fbc8))
152
+ * update PINYIN_TONE_PATTERN and NormalizerZh ([7d943b3](https://github.com/nicokim/indextts2-inference/commit/7d943b362dbc950edc2dfc1fb7726dbfd5d39b81))
153
+ * Use WeTextProcessing on Linux, and wetext on other platforms ([dcdb061](https://github.com/nicokim/indextts2-inference/commit/dcdb0614bf7fc29fe560969324478c29928b1695))
154
+ * **webui.py:** replace return statements with warnings and update markdown table ([fa7962f](https://github.com/nicokim/indextts2-inference/commit/fa7962f1f2decd7a430d2d62544d2e3a3e596d06))
155
+ * **webui.py:** strip tailing whitespace for glossary terms ([6b6606a](https://github.com/nicokim/indextts2-inference/commit/6b6606a2f4d1974ea8ae1413e609b7a17af882fc))
156
+ * **webui:** Add support for Gradio 5.45.0 and higher ([ef09710](https://github.com/nicokim/indextts2-inference/commit/ef097101b7ab70120250c9c3f6394174e656590e))
157
+ * **webui:** Experimental checkbox bugfixes and add visual warning label ([ec368de](https://github.com/nicokim/indextts2-inference/commit/ec368de9329c7beffa3df369005c7d25e7684980))
158
+ * **webui:** Fix unintentional empty spacing between control groups ([f041d8e](https://github.com/nicokim/indextts2-inference/commit/f041d8eb64e1af1f7a5def01247d564b1a283a5b))
159
+ * **webui:** Make the Advanced Settings visible by default again ([e185fa1](https://github.com/nicokim/indextts2-inference/commit/e185fa1ce748de6759f772f3852024c5443724f3))
160
+ * **webui:** Make the Emotion Control Weight slider visible again ([c5f9a31](https://github.com/nicokim/indextts2-inference/commit/c5f9a311275447707791c2758a2267dd137142f2))
161
+ * **webui:** New default emo_alpha recommendation instead of scaling ([1520d06](https://github.com/nicokim/indextts2-inference/commit/1520d0689baa4bacbf095e1c715417de555c123d))
162
+ * 中文readme标题显示问题 ([ce2f71a](https://github.com/nicokim/indextts2-inference/commit/ce2f71aae5b568c17428903aa3f8890c10fe4d26))
163
+ * 修复样本音频太长报错的问题,对音频进行裁切。 ([2cfc76a](https://github.com/nicokim/indextts2-inference/commit/2cfc76ad9c49b4376e3d10a5bfeafbad9e5b5cd3))
164
+ * 添加英语缩写处理 ([414f2a4](https://github.com/nicokim/indextts2-inference/commit/414f2a4052b49248a4ff99380bb84040d0c6e22a))
165
+ * 添加英语缩写处理 ([bb4d76a](https://github.com/nicokim/indextts2-inference/commit/bb4d76aa2a1b5e3efb00ccc6ee7fc45e453f2701))
166
+ * 避免在 MinGW-w64 环境 jit compile cuda ext ([92bb2eb](https://github.com/nicokim/indextts2-inference/commit/92bb2eb0c0a5242943fb86950ce68c73576053a4))
167
+
168
+
169
+ ### Documentation
170
+
171
+ * Add a stronger warning about unsupported installation methods ([6c76807](https://github.com/nicokim/indextts2-inference/commit/6c768073e9519fa253090d539779e2d31be03cf5))
172
+ * Add Alibaba's high-bandwidth PyPI mirror for China ([30848ef](https://github.com/nicokim/indextts2-inference/commit/30848efd45f91d55b7f79f7f4a9388c74077afd7))
173
+ * Add FP16 usage advice for faster inference ([d777b8a](https://github.com/nicokim/indextts2-inference/commit/d777b8a0290cced0064eb5f503a25b65b148c1bc))
174
+ * Add quick uv installation technique ([429c06c](https://github.com/nicokim/indextts2-inference/commit/429c06c787115b4036330181e392785aa9b971f9))
175
+ * Add usage note regarding random sampling ([c3d7ab4](https://github.com/nicokim/indextts2-inference/commit/c3d7ab4adce98e8f46edb1a31374f2f64d72f51c))
176
+ * Clarify that UV handles Python and the environment creation ([cc9c6b6](https://github.com/nicokim/indextts2-inference/commit/cc9c6b6cfe49c6d9e6f84247b785ac08a2c808f5))
177
+ * Document the DeepSpeed performance effects ([85ba55a](https://github.com/nicokim/indextts2-inference/commit/85ba55a1d3ac92006f898115600f2cfef4e34251))
178
+ * Document the new `emo_alpha` feature for text-to-emotion mode ([3b5b6bc](https://github.com/nicokim/indextts2-inference/commit/3b5b6bca85ad01955bf773686647c3983e737dd9))
179
+ * Install HuggingFace CLI with high-speed download feature ([5471d82](https://github.com/nicokim/indextts2-inference/commit/5471d8256fc7867772030b1c0c75fe633f49ea76))
180
+ * Remove redundant "python" command instruction ([242604d](https://github.com/nicokim/indextts2-inference/commit/242604d27e63fba64df00985eb365013e7019bbe))
181
+ * Remove redundant "python" command instruction ([3236fa4](https://github.com/nicokim/indextts2-inference/commit/3236fa496a1d3ed587feb2b24fc85877aea51554))
@@ -0,0 +1,43 @@
1
+ TTS语音合成技术免责声明
2
+
3
+ 1. 总则
4
+ 本声明适用于 Index-TTS(以下简称"本项目")的所有用户和使用者。使用本项目即表示您已阅读、理解并同意遵守本免责声明的全部内容。
5
+
6
+ 2. 使用限制
7
+ 2.1 本项目仅供用户进行技术研究、学习和合法的创意应用,不得用于任何违反法律法规的活动。
8
+
9
+ 2.2 用户不得使用本项目:
10
+ a) 合成政治人物、公众人物或任何未经授权的个人声音;
11
+ b) 创建诋毁、侮辱、歧视或损害他人名誉和权益的内容;
12
+ c) 进行欺诈、身份盗用或任何形式的违法活动;
13
+ d) 传播虚假信息或制造社会恐慌;
14
+ e) 侵犯他人知识产权、肖像权或隐私权;
15
+ f) 未经授权将合成声音用于商业目的;
16
+ g) 违反特定行业(如金融、医疗等)的法规要求;
17
+ h) 创建或使用涉及未成年人的不当声音内容;
18
+ i) 制作可能威胁国家安全的内容;
19
+ j) 违反任何地区关于深度伪造技术的法律法规。
20
+
21
+ 3. 知识产权与授权
22
+ 3.1 本项目以[开源许可证类型]许可证开源。
23
+ 3.2 用户在使用本项目过程中产生的所有内容及其法律责任由用户自行承担。
24
+
25
+ 4. 责任限制
26
+ 4.1 项目开发者不对用户使用本项目所产生的任何直接或间接后果承担责任。
27
+ 4.2 项目开发者不保证本项目的功能满足用户的所有需求,也不保证运行不会中断或出错。
28
+ 4.3 用户因使用本项目而产生的任何法律纠纷、损失或损害,项目开发者概不负责。
29
+
30
+ 5. 法律适用
31
+ 5.1 本免责声明受[国家/地区]法律管辖。
32
+ 5.2 如本声明的任何条款与适用法律相抵触,则以适用法律为准。
33
+
34
+ 6. 声明更新
35
+ 6.1 项目开发者保留随时更新本免责声明的权利,更新后的声明自发布之日起生效。
36
+ 6.2 用户应定期查阅本声明以了解任何变更。
37
+
38
+ 7. 其他条款
39
+ 7.1 用户在使用本项目前,应确保其使用行为符合所在地区的法律法规。
40
+ 7.2 如用户对本项目的使用引起任何法律纠纷,用户应积极配合相关调查并承担相应责任。
41
+
42
+ 最后更新日期:2025.3.17
43
+ 开发者:Bilibili Index Team
@@ -0,0 +1,57 @@
1
+ bilibili Model Use License Agreement
2
+
3
+ By clicking “I agree” to this bilibili Model Use License Agreement (“this Agreement”) , or by otherwise using any portion or element of the Model or any Derivative Work, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately. If you do not agree to this Agreement, you must immediately cease all use and permanently delete the Model and any Derivative Works.
4
+
5
+ 1. Definitions
6
+ 1.1 “This Agreement”: means the bilibili Model Use License Agreement, including all of its terms and conditions.
7
+ 1.2 “We”, “us”, or “our”: means bilibili , the original right-holder of the Model.
8
+ 1.3 “You”: means any natural person or legal entity exercising rights granted by this Agreement and/or using the Model for any purpose and in any field of use.
9
+ 1.4 “Model”: means the artificial-intelligence model named “bilibili indextts2”, including but not limited to model weights and final code, in each case only to the extent that such components are published by us at https://github.com/index-tts/index-tts.
10
+ 1.5 “Derivative Work”: means any derivative of the Model, including without limitation:
11
+  (i) any modification of the Model, model outputs, or their derivatives;
12
+  (ii) any work based on the Model, model outputs, or their derivatives;
13
+  (iii) any other machine learning model which is created by re-training, fine-tuning, quantizing, LoRA, parameter-efficient fine-tuning, or any other method involving incremental weights or merged checkpoints, in each case based on the Model, model outputs, or their derivatives.
14
+ 1.6 “Use”: means downloading, copying, training, modifying, creating Derivative Works, distributing, publishing, running, fine-tuning, publicly displaying, communicating to the public, or otherwise exploiting the Model or any Derivative Work.
15
+
16
+ 2. Scope of License and Restrictions
17
+ 2.1 Subject to the terms and conditions of this Agreement, we grant you a worldwide, non-exclusive, non-transferable, royalty-free limited license to Use the Model or any Derivative Work based on the intellectual properties or other rights owned by Us embodied in the Model or any Derivative Work.
18
+ 2.2 If You intend to Use, or have already Used, the Model or any Derivative Work, and either (i) your or any of your Affiliates’ products or services had more than 100 million monthly active users in the immediately preceding calendar month, or (ii) your or any of your Affiliates’ annual revenue in the immediately preceding calendar year exceeded RMB 1 billion, You must request a separated license from us, which We may grant to You in our sole discretion. You are not authorized to exercise any of the rights under this Agreement unless and until We have expressly granted You such rights in writing.
19
+ 2.3 This Agreement is an open-source license for the Model in which we possess intellectual properties and other rights. It governs your Use of the Model only and does not limit any rights that we have regarding the Model.
20
+
21
+ 3. Disclaimer and Risk Allocation
22
+ 3.1 The Model and any outputs generated thereby are provided “AS IS,” without warranty of any kind, express or implied, including but not limited to warranties of merchantability, fitness for a particular purpose, non-infringement, absence of errors or omissions, continuity, accuracy, reliability, or stability. You are solely responsible for determining the appropriateness of using or redistributing the Model and assume all risks associated with exercising any rights granted under this Agreement.
23
+ 3.2 You shall bear sole responsibility for any infringement, illegality, breach of contract, damages, fines, regulatory investigations, or other liabilities (including, without limitation, infringement of third-party patents, copyrights, trademarks, trade secrets, personality rights, data-protection rights, or any other rights) arising out of or related to your Use of the Model or any outputs generated thereby. We assume no joint, several, supplementary, or advance payment liability.
24
+ 3.3 Under no circumstances shall we be liable to you or any third party for any direct, indirect, incidental, special, punitive, or consequential damages (including, without limitation, loss of data, business interruption, or loss of profits) arising out of or related to the Use of the Model, even if we have been advised of the possibility of such damages.
25
+ 3.4 Additional Obligations for You and Downstream Recipients
26
+ a) You must ensure that any downstream recipient of the Model or any Derivative Work that you distribute complies with this Agreement, and you must impose appropriate contractual terms on such downstream recipients. If any downstream recipient breaches this Agreement, you shall be responsible for the consequences thereof.
27
+ b) You must retain all original copyright notices and a copy of this Agreement in every copy of the Model or any Derivative Work that you Use.
28
+ c) You may not Use the bilibili indextts2 or any Derivative Work to improve any AI model, except for the bilibili indextts2 itself, its Derivative Works,or non-commercial AI models.
29
+
30
+ 4. Compliance Obligations
31
+ 4.1 Usage Restrictions
32
+ a) If you distribute a Derivative Work, you must clearly state in the distribution page or accompanying documentation: “Any modifications made to the original model in this Derivative Work are not endorsed, warranted, or guaranteed by the original right-holder of the original model, and the original right-holder disclaims all liability related to this Derivative Work.”
33
+ b) If your Use of the Model or any Derivative Work incorporates any third-party data or weights, you must obtain all necessary authorizations on your own and bear full responsibility for compliance.
34
+ c) You may not Use the Model or any Derivative Work for any purpose that violates the laws or regulatory requirements of the jurisdiction where the outputs and/or the Model are generated or used (including, without limitation, generating false information, discriminatory content, or content that infringes privacy).
35
+ d) If the Model or any Derivative Work is capable of generating content, you must ensure that such content does not violate the laws or regulatory requirements of the applicable jurisdiction (including, without limitation, generating false information, discriminatory content, or content that infringes privacy).
36
+ 4.2 Prohibited High-Risk Use
37
+ You must ensure that the Model and any Derivative Work are not deployed, directly or indirectly, in high-risk scenarios such as medical diagnosis, autonomous driving, military applications, critical-infrastructure control, large-scale biometric surveillance, or automated decision-making (e.g., credit or employment evaluations). If you insist on such deployment, you must independently complete all compliance obligations under applicable laws and regulations (including but not limited to GDPR, CCPA, HIPAA, export-control laws, and AI-specific regulations), and we shall bear no liability for any consequences arising therefrom.
38
+ 4.3 Infringement Liability
39
+ Should any third party raise claims against you with respect to any Derivative Work you develop or your Use of the Model or any Derivative Work, you shall bear full and independent responsibility for defending against and resolving such claims. If your actions cause us to incur any third-party claims, administrative penalties, or other losses, you shall indemnify us for all losses we thereby suffer, including but not limited to attorney fees, litigation costs, damages, and fines, and shall take all necessary measures to eliminate any adverse impact on us.
40
+
41
+ 5. Reserved Rights
42
+ 5.1 We reserve the right to revoke the license granted to you under this Agreement in the event of your breach. Upon revocation, you must immediately cease all Use and permanently delete all copies of the Model and any Derivative Work. Sections 3 and 6 of this Agreement shall survive termination of this Agreement under this circumstance.
43
+ 5.2 Nothing in this Agreement grants you any right to use our trade names, trademarks, service marks, or product names, except as reasonably and customarily required to describe the origin of the Model or any Derivative Work—such as reproducing the content of a NOTICE file under Section 3.4 of this Agreement.
44
+ 5.3 If you or any of your Affiliates institutes or participates in any legal proceeding (including any cross-claim or counterclaim in a lawsuit) against us or any of our Affiliates, alleging that the Model or any output or any portion thereof infringes any intellectual property or other rights that you own or control, all licenses granted to you under this Agreement shall terminate automatically as of the date such proceeding is filed.
45
+
46
+ 6. Governing Law and Dispute Resolution
47
+ 6.1 This Agreement shall be governed by and construed in accordance with the laws of the People’s Republic of China.
48
+ 6.2 In the event of any dispute arising out of or in connection with this Agreement, the parties shall first attempt to resolve such dispute through friendly negotiation. If negotiation fails, the dispute shall be submitted to the Shanghai Arbitration Commission for arbitration in accordance with its then-effective arbitration rules. The arbitration award shall be final and binding on both parties. The prevailing party shall be entitled to recover reasonable costs, including notarization and investigation fees, arbitration costs, attorneys’ fees, and travel expenses.
49
+
50
+ 7. Severability
51
+ If any provision of this Agreement is held to be invalid or unenforceable, the remaining provisions shall remain in full force and effect. The invalid or unenforceable provision shall be replaced with a valid and enforceable provision that, to the maximum extent permitted by law, most closely reflects the original intent of the invalid or unenforceable provision.
52
+
53
+ 8. Version Updates
54
+ We may release new versions of the AI Model Use License Agreement. Any new version will apply only to Uses occurring after the date of its release. If you obtained the Model under an earlier version, the new version will not have retroactive effect; nevertheless, you are encouraged to adopt the new version voluntarily.
55
+
56
+ 9. Language Version
57
+ In the event of any discrepancy or conflict between the English-language version set forth above and the Chinese-language version of this bilibili Model Use License Agreement, the Chinese-language version shall prevail for all purposes and shall govern the rights and obligations of the parties.
@@ -0,0 +1,52 @@
1
+ bilibili模型使用许可协议
2
+
3
+ 若您点击同意《bilibili模型使用许可协议》(“本协议”),或使用我方模型或衍生品的任何部分或元素,即视为您已确认并接受本协议内容,本协议立即生效。若您不同意本协议,应立即停止使用并删除模型及衍生品。
4
+
5
+ 1.定义
6
+ 1.1 本协议:指《bilibili 模型使用许可协议》,包括本协议所规定的所有条款和条件。
7
+ 1.2 我方:指bilibili即模型的原始权利人。
8
+ 1.3 您:指行使本许可协议授予的权利和/或使用“模型”的自然人或法人实体。
9
+ 1.4 模型:指名为“bilibili indextts2”的AI模型,包括模型权重、最终代码等组件,具体范围以我方在https://github.com/index-tts/index-tts发布的组件为限。
10
+ 1.5 衍生品:指模型的衍生品,包括但不限于:(i)对模型、模型输出及其衍生品的修改;(ii)基于模型、模型输出及其衍生品的创作;(iii)对模型、模型输出及其衍生品再训练、微调、量化、LoRA、参数高效微调、以任何增量权重或合并的检查点等方式创建的任何模型。
11
+ 1.6 使用:指通过下载、复制、训练、修改、创作衍生品、分发、发布、运行、微调、公开展示、传播或以其他方式利用本模型或其衍生品的行为。
12
+
13
+ 2. 许可范围和限制
14
+ 2.1 根据本协议的条款与条件,基于对模型或其衍生品中包含的我方拥有的任何知识产权和其他权利,我方特此授予您一项全球范围、非独占、不可转让、免费的使用许可。
15
+ 2.2若您拟使用或者已使用我方模型或其衍生品,如果您或者您的关联方提供的产品或服务在前一自然月的月活跃用户数超过1亿,或者如果您或者您的关联方在上一自然年的年收入超过1亿人民币的,您必须向我方申请该模型或其衍生品的商业许可,我方可自行决定是否授予您该许可。您无权行使本协议项下的任何权利,除非我方另行明确授予您该等许可。
16
+ 2.3 本协议作为我方享有知识产权和其他权利的模型的开源许可协议,仅约束您对我方模型的使用行为,并不限制我方对该模型享有的任何权利。
17
+
18
+ 3. 免责声明与风险约定
19
+ 3.1 模型及其任何输出均“按原样”提供,我方及其关联方不提供任何形式的明示或暗示的保证,包括但不限于适销性、特定用途适用性、不侵权、没有错误或疏漏、持续性、准确性、可靠性、稳定性的保证。您需自行负责判断使用或再分发本作品的适当性,并承担行使本许可证所授予权限相关的所有风险。
20
+ 3.2 您因使用模型或利用其输出内容而产生的任何侵权、违法、违约、赔偿、罚款、监管调查或其他法律责任(包括但不限于侵犯第三方专利、版权、商标、商业秘密、人格权、数据保护权等),均由您独自承担。我方不承担任何连带责任、补充责任或垫付责任。
21
+ 3.3 在任何情况下,我方对因使用本模型而产生的任何直接、间接、附带、特殊、惩罚性或后果性损失(包括但不限于数据丢失、业务中断、利润损失等)不承担责任,即使我方已被告知该等损失的可能性。
22
+ 3.4 对您和下游用户的其他约束
23
+ a)您应确保下游用户在使用您发布的本模型或您基于本模型开发的衍生品时,同样遵守本协议的相关规定,并通过合适的协议或条款对下游用户进行约束。若下游用户违反本协议规定,您需承担相应责任。
24
+ b)您需在您使用的本模型或您基于本模型开发的衍生品的所有副本中保留原始版权声明及本使用许可协议。
25
+ c)您不得使用bilibili indextts2或其衍生品来改进任何AI模型(bilibili indextts2或其衍生品、非商业用途的AI模型除外)。
26
+
27
+ 4. 合规义务
28
+ 4.1使用限制
29
+ a) 若您发布模型的衍生品,必须在发布页面或附随文档中清晰声明“该衍生品对原模型所作的任何改动与原模型原始权利人无关,原始权利人对该衍生品不背书、不担保、不承担责任”。
30
+ b) 若您使用模型或模型衍生品的过程中引入任何第三方数据或权重,您须自行取得合法授权并承担全部合规责任。
31
+ c) 不得将模型及模型衍生品用于违反输出地/使用地法律或监管要求的用途(包括但不限于生成虚假信息、歧视性内容、侵犯隐私等)。
32
+ d) 若模型或模型衍生品具备生成内容功能,您须确保其输出内容不违反输出地/使用地法律或监管要求的用途(包括但不限于生成虚假信息、歧视性内容、侵犯隐私等)。
33
+ 4.2 禁止高风险场景
34
+ 您须自行确保不在医疗诊断、自动驾驶、军事、关键基础设施控制、大规模生物识别监控、自动化决策(如信贷、就业评估)等高风险场景直接部署本模型及其衍生品。若您坚持部署,应自行完成符合适用法规(包括 GDPR、CCPA、HIPAA、出口管制、AI 特定法规等)的全部合规要求,我方对因此产生的任何后果概不负责。
35
+ 4.3 侵权责任
36
+ 如第三方就您开发的模型衍生品或您使用模型或其衍生品等行为主张权利,您应独立承担全部责任。若因您的行为导致我方遭受任何第三方索赔、行政处罚或其他损失,您应负责赔偿我方因此遭受的全部损失,包括但不限于律师费、诉讼费、赔偿金、罚款等,并采取一切必要措施消除对我方的负面影响。
37
+
38
+ 5. 保留权利
39
+ 5.1我方保留在您违反协议的情况下撤销本协议对您授权之权利。协议撤销后,您必须立即删除并停止使用材料。在本协议终止后,本协议第3条、第6条仍然有效。
40
+ 5.2 本许可证不授予使用我方的商号、商标、服务标记或产品名称的权限,除非在合理且惯例性地描述模型或衍生品的来源,例如本许可证3.4的规定,以及复制 NOTICE 文件内容时需要使用。
41
+ 5.3 若您或您的关联方对我方或我方任何关联实体提起诉讼或其他程序(包括诉讼中的交叉索赔或反诉),主张模型或其任何输出结果或其任何部分侵犯了您拥有或可许可的知识产权或其他权利,则本协议授予您的所有许可自该诉讼或程序提起之日起终止。
42
+
43
+ 6. 法律适用与争议解决
44
+ 6.1 本协议适用中华人民共和国法律法规。
45
+ 6.2 在本协议履行中,若发生争议,双方应本着友好协商的原则解决问题;如协商不成,双方均应将争议提交至上海仲裁委员会根据其仲裁规则进行仲裁,仲裁是一裁终局的,对双方均有约束力。由仲裁败诉方承担本次仲裁产生的公证调查费、仲裁费、律师费、差旅费等实际产生费用。
46
+
47
+ 7. 可分割性
48
+ 若本协议任何条款被认定为无效或不可执行,不影响其余条款之效力;无效部分应在法律允许的最大范围内按最接近原意的有效条款替代。
49
+
50
+ 8. 协议版本更新
51
+ 我方可发布新版 AI模型使用许可协议。新版仅适用于发布后新产生的使用行为,若您已按旧版获取模型,新版协议并无溯及力,但鼓励您主动更新。
52
+
@@ -0,0 +1,45 @@
1
+ Metadata-Version: 2.4
2
+ Name: indextts2-inference
3
+ Version: 2.0.1
4
+ Summary: IndexTTS2 inference library: zero-shot text-to-speech with emotional control
5
+ Author: Bilibili IndexTTS Team
6
+ License-Expression: LicenseRef-Bilibili-IndexTTS
7
+ License-File: LICENSE
8
+ License-File: LICENSE_ZH.txt
9
+ Classifier: Development Status :: 4 - Beta
10
+ Classifier: Intended Audience :: Developers
11
+ Classifier: Intended Audience :: Science/Research
12
+ Classifier: Natural Language :: Chinese (Simplified)
13
+ Classifier: Natural Language :: English
14
+ Classifier: Operating System :: OS Independent
15
+ Classifier: Programming Language :: Python :: 3
16
+ Classifier: Topic :: Scientific/Engineering
17
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
18
+ Requires-Python: >=3.10
19
+ Requires-Dist: accelerate>=1.0
20
+ Requires-Dist: cn2an>=0.5
21
+ Requires-Dist: einops>=0.8
22
+ Requires-Dist: g2p-en>=2.1
23
+ Requires-Dist: huggingface-hub>=0.20
24
+ Requires-Dist: jieba>=0.42
25
+ Requires-Dist: json5>=0.9
26
+ Requires-Dist: librosa>=0.10
27
+ Requires-Dist: munch>=4.0
28
+ Requires-Dist: omegaconf>=2.3
29
+ Requires-Dist: safetensors>=0.4
30
+ Requires-Dist: sentencepiece>=0.2
31
+ Requires-Dist: tokenizers>=0.19
32
+ Requires-Dist: torch>=2.0
33
+ Requires-Dist: torchaudio>=2.0
34
+ Requires-Dist: torchcodec>=0.10
35
+ Requires-Dist: tqdm>=4.60
36
+ Requires-Dist: transformers>=5.0
37
+ Requires-Dist: wetext>=0.0.9
38
+ Provides-Extra: deepspeed
39
+ Requires-Dist: deepspeed>=0.14; extra == 'deepspeed'
40
+ Provides-Extra: es
41
+ Requires-Dist: nemo-text-processing>=1.1; extra == 'es'
42
+ Provides-Extra: flash-attn
43
+ Requires-Dist: flash-attn>=2.1; extra == 'flash-attn'
44
+ Provides-Extra: sage-attn
45
+ Requires-Dist: sageattention>=1.0; extra == 'sage-attn'