first commit

LICENSE

+
+
+                                 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 2018-2020 Open-MMLab.
+
+   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.

README.md

+# Maya1
+## 论文
+暂无
+
+## 模型简介
+Maya1是一款先进的语音模型，用于生成富有表现力的声音，旨在捕捉真实的人类情感和精确的语音设计。具有如下功能：
+-创造你能想象到的任何声音 —— 20年代的英国女孩、美国小伙，或者一个完整的恶魔。
+-使用情感标签使其感觉真实：笑、哭、低语、愤怒、叹息、喘息。
+-即时流式传输，听起来生动，3B参数，在单个GPU上运行
+-超越顶级专有模型。由Maya Research开发。
+
+## 环境依赖
+- 列举基础环境需求，根据实际情况填写
+
+| 软件 | 版本 |
+| :------: | :------: |
+| DTK | 25.04.2 |
+| python | 3.10 |
+| transformers | 4.57.1 |
+| pytorch | 2.7.1+das.opt1.dtk25042 |
+
+推荐使用镜像:
+- 挂载地址`-v`，`{docker_name}`和 `{docker_image_name}`根据实际模型情况修改
+
+```bash
+docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.7.1-ubuntu22.04-dtk25.04.2-py3.10-alpha
+docker run -it --shm-size 200g --network=host --name {docker_name} --privileged --device=/dev/kfd --device=/dev/dri --device=/dev/mkfd --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro {imageID} bash
+
+cd /your_code_path/maya1_pytorch
+pip install -r requirements.txt
+
+```
+更多镜像可前往[光源](https://sourcefind.cn/#/service-list)下载使用。
+
+关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.sourcefind.cn/tool/)开发者社区下载安装，其它包参照requirements.txt安装：
+```
+pip install -r requirements.txt
+```
+
+## 数据集
+
+暂无
+
+## 训练
+暂无
+
+## 推理
+
+### transformers
+#### 单机推理
+```bash
+export HF_ENDPOINT=https://hf-mirror.com
+export HIP_VISIBLE_DEVICES=0
+python mya.py
+```
+
+## 效果展示
+
+Text: Hello! This is Maya1 <laugh_harder> the best open source voice AI model with emotions.
+[out.wav](./doc/output.wav)
+
+### 精度
+DCU与GPU精度一致，推理框架：pytorch。
+
+## 预训练权重
+| 模型名称  | 权重大小  | DCU型号  | 最低卡数需求 |下载地址|
+|:-----:|:----------:|:----------:|:---------------------:|:----------:|
+| maya1 | 3B | K100AI,BW1000 | 1 | [下载地址](https://huggingface.co/maya-research/maya1) |
+
+## 源码仓库及问题反馈
+- https://developer.sourcefind.cn/codes/modelzoo/maya1_pytorch
+
+## 参考资料
+- https://huggingface.co/maya-research/maya1

model.properties

+# 模型唯一标识
+modelCode = 1811
+# 模型名称
+modelName= Maya1_pytorch
+# 模型描述
+modelDescription=Maya1是一款先进的语音模型，用于生成富有表现力的声音，旨在捕捉真实的人类情感和精确的语音设计。
+# 应用场景
+processType=推理
+# 算法类别
+appScenario=语音合成
+# 框架类型
+frameType=pytorch
+# 加速卡类型
+accelerateType=BW1000,K100AI
+

mya.py

+#!/usr/bin/env python3
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from snac import SNAC
+import soundfile as sf
+import numpy as np
+
+CODE_START_TOKEN_ID = 128257
+CODE_END_TOKEN_ID = 128258
+CODE_TOKEN_OFFSET = 128266
+SNAC_MIN_ID = 128266
+SNAC_MAX_ID = 156937
+SNAC_TOKENS_PER_FRAME = 7
+
+SOH_ID = 128259
+EOH_ID = 128260
+SOA_ID = 128261
+BOS_ID = 128000
+TEXT_EOT_ID = 128009
+
+
+def build_prompt(tokenizer, description: str, text: str) -> str:
+    """Build formatted prompt for Maya1."""
+    soh_token = tokenizer.decode([SOH_ID])
+    eoh_token = tokenizer.decode([EOH_ID])
+    soa_token = tokenizer.decode([SOA_ID])
+    sos_token = tokenizer.decode([CODE_START_TOKEN_ID])
+    eot_token = tokenizer.decode([TEXT_EOT_ID])
+    bos_token = tokenizer.bos_token
+    
+    formatted_text = f'<description="{description}"> {text}'
+    
+    prompt = (
+        soh_token + bos_token + formatted_text + eot_token +
+        eoh_token + soa_token + sos_token
+    )
+    
+    return prompt
+
+
+def extract_snac_codes(token_ids: list) -> list:
+    """Extract SNAC codes from generated tokens."""
+    try:
+        eos_idx = token_ids.index(CODE_END_TOKEN_ID)
+    except ValueError:
+        eos_idx = len(token_ids)
+    
+    snac_codes = [
+        token_id for token_id in token_ids[:eos_idx]
+        if SNAC_MIN_ID <= token_id <= SNAC_MAX_ID
+    ]
+    
+    return snac_codes
+
+
+def unpack_snac_from_7(snac_tokens: list) -> list:
+    """Unpack 7-token SNAC frames to 3 hierarchical levels."""
+    if snac_tokens and snac_tokens[-1] == CODE_END_TOKEN_ID:
+        snac_tokens = snac_tokens[:-1]
+    
+    frames = len(snac_tokens) // SNAC_TOKENS_PER_FRAME
+    snac_tokens = snac_tokens[:frames * SNAC_TOKENS_PER_FRAME]
+    
+    if frames == 0:
+        return [[], [], []]
+    
+    l1, l2, l3 = [], [], []
+    
+    for i in range(frames):
+        slots = snac_tokens[i*7:(i+1)*7]
+        l1.append((slots[0] - CODE_TOKEN_OFFSET) % 4096)
+        l2.extend([
+            (slots[1] - CODE_TOKEN_OFFSET) % 4096,
+            (slots[4] - CODE_TOKEN_OFFSET) % 4096,
+        ])
+        l3.extend([
+            (slots[2] - CODE_TOKEN_OFFSET) % 4096,
+            (slots[3] - CODE_TOKEN_OFFSET) % 4096,
+            (slots[5] - CODE_TOKEN_OFFSET) % 4096,
+            (slots[6] - CODE_TOKEN_OFFSET) % 4096,
+        ])
+    
+    return [l1, l2, l3]
+
+
+def main():
+    
+    # Load the best open source voice AI model
+    print("\n[1/3] Loading Maya1 model...")
+    model = AutoModelForCausalLM.from_pretrained(
+        "maya-research/maya1", 
+        torch_dtype=torch.bfloat16, 
+        device_map="auto",
+        trust_remote_code=True
+    )
+    tokenizer = AutoTokenizer.from_pretrained(
+        "maya-research/maya1",
+        trust_remote_code=True
+    )
+    print(f"Model loaded: {len(tokenizer)} tokens in vocabulary")
+    
+    # Load SNAC audio decoder (24kHz)
+    print("\n[2/3] Loading SNAC audio decoder...")
+    snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").eval()
+    if torch.cuda.is_available():
+        snac_model = snac_model.to("cuda")
+    print("SNAC decoder loaded")
+    
+    # Design your voice with natural language
+    description = "Realistic male voice in the 30s age with american accent. Normal pitch, warm timbre, conversational pacing."
+    text = "Hello! This is Maya1 <laugh_harder> the best open source voice AI model with emotions."
+    
+    print("\n[3/3] Generating speech...")
+    print(f"Description: {description}")
+    print(f"Text: {text}")
+    
+    # Create prompt with proper formatting
+    prompt = build_prompt(tokenizer, description, text)
+    
+    # Debug: Show prompt details
+    print(f"\nPrompt preview (first 200 chars):")
+    print(f"   {repr(prompt[:200])}")
+    print(f"   Prompt length: {len(prompt)} chars")
+    
+    # Generate emotional speech
+    inputs = tokenizer(prompt, return_tensors="pt")
+    print(f"   Input token count: {inputs['input_ids'].shape[1]} tokens")
+    if torch.cuda.is_available():
+        inputs = {k: v.to("cuda") for k, v in inputs.items()}
+    
+    with torch.inference_mode():
+        outputs = model.generate(
+            **inputs, 
+            max_new_tokens=2048,  # Increase to let model finish naturally
+            min_new_tokens=28,  # At least 4 SNAC frames
+            temperature=0.4, 
+            top_p=0.9, 
+            repetition_penalty=1.1,  # Prevent loops
+            do_sample=True,
+            eos_token_id=CODE_END_TOKEN_ID,  # Stop at end of speech token
+            pad_token_id=tokenizer.pad_token_id,
+        )
+    
+    # Extract generated tokens (everything after the input prompt)
+    generated_ids = outputs[0, inputs['input_ids'].shape[1]:].tolist()
+    
+    print(f"Generated {len(generated_ids)} tokens")
+    
+    # Debug: Check what tokens we got
+    print(f"   First 20 tokens: {generated_ids[:20]}")
+    print(f"   Last 20 tokens: {generated_ids[-20:]}")
+    
+    # Check if EOS was generated
+    if CODE_END_TOKEN_ID in generated_ids:
+        eos_position = generated_ids.index(CODE_END_TOKEN_ID)
+        print(f" EOS token found at position {eos_position}/{len(generated_ids)}")
+    
+    # Extract SNAC audio tokens
+    snac_tokens = extract_snac_codes(generated_ids)
+    
+    print(f"Extracted {len(snac_tokens)} SNAC tokens")
+    
+    # Debug: Analyze token types
+    snac_count = sum(1 for t in generated_ids if SNAC_MIN_ID <= t <= SNAC_MAX_ID)
+    other_count = sum(1 for t in generated_ids if t < SNAC_MIN_ID or t > SNAC_MAX_ID)
+    print(f"   SNAC tokens in output: {snac_count}")
+    print(f"   Other tokens in output: {other_count}")
+    
+    # Check for SOS token
+    if CODE_START_TOKEN_ID in generated_ids:
+        sos_pos = generated_ids.index(CODE_START_TOKEN_ID)
+        print(f"   SOS token at position: {sos_pos}")
+    else:
+        print(f"   No SOS token found in generated output!")
+    
+    if len(snac_tokens) < 7:
+        print("Error: Not enough SNAC tokens generated")
+        return
+    
+    # Unpack SNAC tokens to 3 hierarchical levels
+    levels = unpack_snac_from_7(snac_tokens)
+    frames = len(levels[0])
+    
+    print(f"Unpacked to {frames} frames")
+    print(f"   L1: {len(levels[0])} codes")
+    print(f"   L2: {len(levels[1])} codes")
+    print(f"   L3: {len(levels[2])} codes")
+    
+    # Convert to tensors
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    codes_tensor = [
+        torch.tensor(level, dtype=torch.long, device=device).unsqueeze(0)
+        for level in levels
+    ]
+    
+    # Generate final audio with SNAC decoder
+    print("\n[4/4] Decoding to audio...")
+    with torch.inference_mode():
+        z_q = snac_model.quantizer.from_codes(codes_tensor)
+        audio = snac_model.decoder(z_q)[0, 0].cpu().numpy()
+    
+    # Trim warmup samples (first 2048 samples)
+    if len(audio) > 2048:
+        audio = audio[2048:]
+    
+    duration_sec = len(audio) / 24000
+    print(f"Audio generated: {len(audio)} samples ({duration_sec:.2f}s)")
+    
+    # Save your emotional voice output
+    output_file = "output.wav"
+    sf.write(output_file, audio, 24000)
+    print(f"\nVoice generated successfully!")
+
+
+if __name__ == "__main__":
+    main()
+