sopro 1.0.0__py3-none-any.whl

sopro/tokenizer.py

@@ -0,0 +1,38 @@
+from __future__ import annotations
+
+from typing import List
+
+try:
+    from transformers import AutoTokenizer
+    from transformers import logging as hf_logging
+
+    hf_logging.set_verbosity_error()
+except Exception:
+    hf_logging = None
+    AutoTokenizer = None
+
+
+class TextTokenizer:
+    def __init__(self, model_name: str, add_bos_eos: bool = True):
+        if AutoTokenizer is None:
+            raise ImportError("pip install transformers sentencepiece")
+        self.tok = AutoTokenizer.from_pretrained(model_name, use_fast=True)
+        self.add_bos_eos = add_bos_eos
+
+        if self.tok.pad_token_id is None:
+            self.tok.add_special_tokens({"pad_token": "<|pad|>"})
+
+        self.pad_id = int(self.tok.pad_token_id)
+        self.bos_id = (
+            int(self.tok.bos_token_id) if self.tok.bos_token_id is not None else None
+        )
+        self.eos_id = (
+            int(self.tok.eos_token_id) if self.tok.eos_token_id is not None else None
+        )
+        self.vocab_size = int(self.tok.vocab_size + len(self.tok.get_added_vocab()))
+
+    def encode(self, text: str) -> List[int]:
+        ids = self.tok.encode(text, add_special_tokens=False)
+        if self.add_bos_eos and self.bos_id is not None and self.eos_id is not None:
+            ids = [self.bos_id] + ids + [self.eos_id]
+        return ids

sopro-1.0.0.dist-info/METADATA

@@ -0,0 +1,182 @@
+Metadata-Version: 2.4
+Name: sopro
+Version: 1.0.0
+Summary: A lightweight text-to-speech model with zero-shot voice cloning.
+Author-email: Samuel Vitorino <samvitorino@gmail.com>
+License: Apache 2.0
+Project-URL: Homepage, https://github.com/samuel-vitorino/sopro
+Project-URL: Repository, https://github.com/samuel-vitorino/sopro
+Project-URL: Issues, https://github.com/samuel-vitorino/sopro/issues
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: numpy>=1.23
+Requires-Dist: torch>=2.1
+Requires-Dist: transformers>=4.46.0
+Requires-Dist: huggingface_hub>=0.23
+Requires-Dist: safetensors>=0.4.3
+Requires-Dist: sentencepiece>=0.1.99
+Requires-Dist: soundfile>=0.12.1
+Requires-Dist: torchaudio>=2.1
+Requires-Dist: tqdm>=4.66
+Dynamic: license-file
+
+https://github.com/user-attachments/assets/40254391-248f-45ff-b9a4-107d64fbb95f
+
+# Sopro TTS
+
+[![Alt Text](https://img.shields.io/badge/HuggingFace-Model-orange?logo=huggingface)](https://huggingface.co/samuel-vitorino/sopro)
+
+Sopro (from the Portuguese word for “breath/blow”) is a lightweight English text-to-speech model I trained as a side project. Sopro is composed of dilated convs (à la WaveNet) and lightweight cross-attention layers, instead of the common Transformer architecture. Even though Sopro is not SOTA across most voices and situations, I still think it’s a cool project made with a very low budget (trained on a single L40S GPU), and it can be improved with better data.
+
+Some of the main features are:
+
+- **169M parameters**
+- **Streaming**
+- **Zero-shot voice cloning**
+- **0.25 RTF on CPU** (measured on an M3 base model), meaning it generates 30 seconds of audio in 7.5 seconds
+- **3-12 seconds of reference audio** for voice cloning
+
+---
+
+## Instructions
+
+I only pinned the minimum dependency versions so you can install the package without having to create a separate env. However, some versions of Torch work best. For example, on my M3 CPU, `torch==2.6.0` (without `torchvision`) achieves ~3× more performance.
+
+(Optional)
+
+```bash
+conda create -n soprotts python=3.10
+conda activate soprotts
+```
+
+### From PyPI
+
+```bash
+pip install sopro-tts
+```
+
+### From the repo
+
+```bash
+git clone https://github.com/samuel-vitorino/sopro
+cd sopro
+pip install -e .
+```
+
+---
+
+## Examples
+
+### CLI
+
+```bash
+soprotts \
+  --text "Sopro is a lightweight 169 million parameter text-to-speech model. Some of the main features are streaming, zero-shot voice cloning, and 0.25 real-time factor on the CPU." \
+  --ref_audio ref.wav \
+  --out out.wav
+```
+
+You have the expected `temperature` and `top_p` parameters, alongside:
+
+- `--style_strength` (controls the FiLM strength; increasing it can improve or reduce voice similarity; default `1.0`)
+- `--no_stop_head` to disable early stopping
+- `--stop_threshold` and `--stop_patience` (number of consecutive frames that must be classified as final before **stopping**). For short sentences, the stop head may fail to trigger, in which case you can lower these values. Likewise, if the model stops before producing the full text, adjusting these parameters up can help.
+
+### Python
+
+#### Non-streaming
+
+```python
+from sopro import SoproTTS
+
+tts = SoproTTS.from_pretrained("samuel-vitorino/sopro", device="cpu")
+
+wav = tts.synthesize(
+    "Hello! This is a non-streaming Sopro TTS example.",
+    ref_audio_path="ref.wav",
+)
+
+tts.save_wav("out.wav", wav)
+```
+
+#### Streaming
+
+```python
+import torch
+from sopro import SoproTTS
+
+tts = SoproTTS.from_pretrained("samuel-vitorino/sopro", device="cpu")
+
+chunks = []
+for chunk in tts.stream(
+    "Hello! This is a streaming Sopro TTS example.",
+    ref_audio_path="ref.mp3",
+):
+    chunks.append(chunk.cpu())
+
+wav = torch.cat(chunks, dim=-1)
+tts.save_wav("out_stream.wav", wav)
+```
+
+---
+
+## Interactive streaming demo
+
+![Screenshot](https://github.com/user-attachments/assets/a1902bb9-734c-4da8-ad0d-f842fb7da370)
+
+After you install the `sopro` package:
+
+```bash
+pip install -r demo/requirements.txt
+uvicorn demo.server:app --host 0.0.0.0 --port 8000
+```
+
+Or with docker:
+
+```bash
+docker build -t sopro-demo .
+docker run --rm -p 8000:8000 sopro-demo
+```
+
+Navigate to http://localhost:8000 on your browser.
+
+---
+
+## Disclaimers
+
+- Sopro can be inconsistent, so mess around with the parameters until you get a decent sample.
+- Voice cloning is **highly dependent** on mic quality, ambient noise, etc. On more OOD voices it might fail to match the voice well.
+- Prefer phonemes instead of abbreviations and symbols. For example, `“1 + 2”` → `“1 plus 2”`. That said, Sopro can generally read abbreviations like “CPU”, “TTS”, etc.
+- The streaming version is not bit-exact compared to the non-streaming version. For best quality, prioritize the non-streaming version.
+- If you use torchaudio to read or write audio, ffmpeg may be required. I recommend just using soundfile.
+- I will publish the training code once I have time to organize it.
+
+Due to budget constraints, the dataset used for training was pre-tokenized and the raw audio was discarded (it took up a lot of space). Later in training, I could have used the raw audio to improve the speaker embedding / voice similarity, because some nuances of voice are lost when you compress it with a neural codec into a discrete space.
+
+I didn't lose much time trying to optimize further, but there is still some room for improvement. For example, caching conv states.
+
+Currently, generation is limited to **~32 seconds (400 frames)**. You can increase it, but the model generally hallucinates beyond that.
+
+AI was used mainly for creating the web demo, organizing my messy code into this repo, ablations and brainstorming.
+
+I would love to support more languages and continue improving the model. If you like this project, consider buying me a coffee so I can buy more compute: https://buymeacoffee.com/samuelvitorino
+
+---
+
+## Training data
+
+- [Emilia YODAS](https://huggingface.co/datasets/amphion/Emilia-Dataset)
+- [LibriTTS-R](https://huggingface.co/datasets/mythicinfinity/libritts_r)
+- [Mozilla Common Voice 22](https://datacollective.mozillafoundation.org/)
+- [MLS](https://huggingface.co/datasets/parler-tts/mls_eng_10k)
+
+---
+
+## Acknowledgements
+
+- [Mimi Codec (Kyutai)](https://huggingface.co/kyutai/mimi)
+- [WaveNet](https://arxiv.org/abs/1609.03499)
+- [Attentive Stats Pooling](https://arxiv.org/abs/1803.10963)
+- [AudioLM](https://arxiv.org/pdf/2209.03143)
+- [CSM](https://github.com/SesameAILabs/csm)

sopro-1.0.0.dist-info/RECORD

@@ -0,0 +1,23 @@
+sopro/__init__.py,sha256=zVh0MjV3XHwZaV_4HzQnLE2mNTtM2gtfQ5-k_Ld2dBs,110
+sopro/audio.py,sha256=xlp6aYzzGlOMcNZ-p9lDeeU0TUkSHMcvmLantwg_4-0,4162
+sopro/cli.py,sha256=YKfGalyhbRuvjVrGJuo1NlIC7h8CszlMxuTwhYgUSwQ,5751
+sopro/config.py,sha256=OBD-k2z5GUdjFS545MyBXx-dAGhwnhRG11LW-zQt1-g,1063
+sopro/constants.py,sha256=wSjFKeFIcLCxyVUVb3njxMK666IuxjlNzVT4_jfPovQ,97
+sopro/hub.py,sha256=xsHfeO8X7v__FELvaQxWHYG8P39ygrgbluPs5GQjoCM,1391
+sopro/model.py,sha256=YXwcVGN3v5T0kvKttmo9WNPpewF-b5aOZoTMVypkzO8,28624
+sopro/sampling.py,sha256=Q5rbuef_BIuy12cv5J7v6k9ob3zQ0OFJIlMHssOkiuU,2951
+sopro/streaming.py,sha256=O5Kkl4cUBjzgjTrEwQK2ka5h6sgcYaEZmIp66-obcPM,4975
+sopro/tokenizer.py,sha256=ucb86Jr-EaAyD9OHDoCmwB9Nh9AFIZK_TlZmMkv46KQ,1325
+sopro/codec/__init__.py,sha256=6D6Q0M-SUZZnq79OT1nATenEc8zIZDrhZBpm7zdPEE4,129
+sopro/codec/mimi.py,sha256=RNKnXfhWXUqHiU27C90wj18Rb3R2IZHpm5_cS_XAs9Y,5798
+sopro/nn/__init__.py,sha256=JewW6GvQPMBsCDkmnm9u5G3tvaAzClUVMIgcVH4N7aw,561
+sopro/nn/blocks.py,sha256=zDEVUH2LXapXuQ4DyhplNh1I0iJYrNUL20IxHoz8ucs,3221
+sopro/nn/embeddings.py,sha256=7YfYKj1v1oafTV4-iucJG4fmeT43fP_rQiJ6ACRKPNI,3185
+sopro/nn/speaker.py,sha256=L2bs-bPlyxoWZyMTctBBuMTaEWm6FP7K1udrXehnTGM,2964
+sopro/nn/xattn.py,sha256=OeRo1HbRZs0AkQ6AV6Q8cqYZP9K4vI-IwT3uVn9jOqg,2939
+sopro-1.0.0.dist-info/licenses/LICENSE.txt,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sopro-1.0.0.dist-info/METADATA,sha256=iXQQ7IjPssmpTXfQ4CwMOVYyeojR7kQYv74jhx5u8Z8,6474
+sopro-1.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sopro-1.0.0.dist-info/entry_points.txt,sha256=OWcKgC5Syk8rzOhNzTZ3QR5GJEG88UfiShkovrwb2cI,44
+sopro-1.0.0.dist-info/top_level.txt,sha256=Tik26_lEwzSKDuwQdqwoqA_O0b7CDATzousa0Q17PBo,6
+sopro-1.0.0.dist-info/RECORD,,

sopro-1.0.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

sopro-1.0.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+soprotts = sopro.cli:main

sopro-1.0.0.dist-info/licenses/LICENSE.txt

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

sopro-1.0.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+sopro