No official torrent yet โ requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from OpenMOSS-Team/MOSS-TTS-v1.5
All models by OpenMOSS-Team โย ย ย ย
MOSS-TTS-v1.5 is continued from MOSS-TTS 1.0. It preserves the main 1.0 capabilities, including zero-shot voice cloning, long-form speech generation, token-level duration control, Pinyin/IPA pronunciation control, multilingual synthesis, and code-switching. For the full 1.0 feature walkthrough, input schema, decoding hyperparameters, and evaluation tables, please refer to the MOSS-TTS 1.0 README.
Compared with MOSS-TTS 1.0, v1.5 focuses on the following improvements:
language field is omitted, v1.5 may improve some languages and regress slightly on others compared with 1.0. When the language is specified, v1.5 is stronger than 1.0 on almost all supported languages. Set the tag when building the user message, for example processor.build_user_message(text=text_fr, language="French")."[pause 3.2s]". For example, ๆไปๅคฉๅญฆไน ไบไธ้ฆไธญๅฝ็ๅค่ฏ๏ผๅฎ็ๅๅญๆฏ[pause 3.2s]้ๅคๆ๏ผ inserts an explicit 3.2s pause before ้ๅคๆ.MOSS-TTS-v1.5 currently supports 31 languages. It keeps the 20 languages supported by MOSS-TTS 1.0 and extends multilingual continued training to additional languages including Cantonese, Dutch, Finnish, Hindi, Macedonian, Malay, Romanian, Swahili, Tagalog, Thai, and Vietnamese.
We recommend a clean, isolated Python environment with Transformers 5.0.0 to avoid dependency conflicts.
Install all required dependencies:
For better speed and lower GPU memory usage, you can install FlashAttention 2 if your hardware supports it.
If your machine has limited RAM and many CPU cores, you can cap build parallelism:
Notes:
pyproject.toml, which currently pins torch==2.9.1+cu128 and torchaudio==2.9.1+cu128.torch.float16 or torch.bfloat16.Tip: MOSS-TTS-v1.5 uses the same generation API as the 1.0 MossTTSDelay-8B checkpoint. For multilingual inputs, set
languagewhenever the language is known.
MOSS-TTS provides a convenient generate interface for rapid usage. The examples below cover:
[pause X.Ys]MOSS-TTS-v1.5 is API-compatible with MOSS-TTS 1.0. For continuation with prefix audio, detailed UserMessage and AssistantMessage fields, generation hyperparameters, Pinyin/IPA preprocessing examples, and evaluation results, see the MOSS-TTS 1.0 README.
conda create -n moss-tts python=3.12 -yconda activate moss-ttsgit clone https://github.com/OpenMOSS/MOSS-TTS.gitcd MOSS-TTSpip install --extra-index-url https://download.pytorch.org/whl/cu128 -e .pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[flash-attn]"MAX_JOBS=4 pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[flash-attn]"from pathlib import Pathimport importlib.utilimport torchimport torchaudiofrom transformers import AutoModel, AutoProcessor# Disable the broken cuDNN SDPA backendtorch.backends.cuda.enable_cudnn_sdp(False)# Keep these enabled as fallbackstorch.backends.cuda.enable_flash_sdp(True)torch.backends.cuda.enable_mem_efficient_sdp(True)torch.backends.cuda.enable_math_sdp(True)
pretrained_model_name_or_path = "OpenMOSS-Team/MOSS-TTS-v1.5"device = "cuda" if torch.cuda.is_available() else "cpu"dtype = torch.bfloat16 if device == "cuda" else torch.float32
def resolve_attn_implementation() -> str: # Prefer FlashAttention 2 when package + device conditions are met. if ( device == "cuda" and importlib.util.find_spec("flash_attn") is not None and dtype in {torch.float16, torch.bfloat16} ): major, _ = torch.cuda.get_device_capability() if major >= 8: return "flash_attention_2"
# CUDA fallback: use PyTorch SDPA kernels. if device == "cuda": return "sdpa"
# CPU fallback. return "eager"
attn_implementation = resolve_attn_implementation()print(f"[INFO] Using attn_implementation={attn_implementation}")
processor = AutoProcessor.from_pretrained( pretrained_model_name_or_path, trust_remote_code=True,)processor.audio_tokenizer = processor.audio_tokenizer.to(device)
text_1 = "ไบฒ็ฑ็ไฝ ๏ผ\nไฝ ๅฅฝๅใ\n\nไปๅคฉ๏ผๆๆณ็จๆ่ฎค็ใๆๆธฉๆ็ๅฃฐ้ณ๏ผๅฏนไฝ ่ฏดไธไบ้่ฆ็่ฏใ\n่ฟไบ่ฏ๏ผๅไธ้ขๅฐๅฐ็ๆๆ๏ผๅธๆ่ฝๅจไฝ ็ๅฟ้ๆ
ขๆ
ขๅๅ
ใ\n\n้ฆๅ
๏ผๆๆณ็ฅไฝ โโ\nๆฏๅคฉ้ฝ่ฝๅนณๅนณๅฎๅฎใๅฟซๅฟซไนไนใ\n\nๅธๆไฝ ๆฉไธ้ๆฅ็ๆถๅ๏ผ\n็ชๅคๆๅ
๏ผๅฑๅญ้ๅพๅฎ้๏ผ\nไฝ ็ๅฟๆฏ่ฝป่ฝป็๏ผๆฒกๆ็ๆฅ๏ผไนๆฒกๆๅฎณๆใ\n\nๅธๆไฝ ๅ้ฅญ็ๆถๅ่ๅฃๅพๅฅฝ๏ผ\n่ตฐ่ทฏ็ๆถๅ่ๆญฅ็จณ็จณ๏ผ\nๆไธ็ก่ง็ๆถๅ๏ผ่ฝๅไธไธชๅไธไธช็็็ๆขฆใ\n\nๆๅธๆไฝ ่ฝไธ็ดไฟๆๅฅฝๅฅๅฟใ\nๅฏนไธ็ๅ
ๆปก้ฎ้ข๏ผ\nๅฏนๅคฉ็ฉบใๆๆใ่ฑ่ใไนฆๆฌๅๆ
ไบๆๅ
ด่ถฃใ\nๅฝไฝ ้ฎโไธบไปไนโ็ๆถๅ๏ผ\nๅธๆๆปๆไบบๆฟๆ่ฎค็ๅฐๅฌไฝ ่ฏด่ฏใ\n\nๆไนๅธๆไฝ ๅญฆไผๆธฉๆใ\nๆธฉๆๅฐๅฏนๅพ
ๆๅ๏ผ\nๆธฉๆๅฐๅฏนๅพ
ๅฐๅจ็ฉ๏ผ\nไนๆธฉๆๅฐๅฏนๅพ
่ชๅทฑใ\n\nๅฆๆๆไธๅคฉไฝ ็ฏไบ้๏ผ\n่ฏทไธ่ฆๅคชๅฟซ่ดฃๆช่ชๅทฑ๏ผ\nๅ ไธบๆฏไธไธช่ฎค็ๆ้ฟ็ไบบ๏ผ\n้ฝไผๅจ่ทฏไธๆ
ขๆ
ขๅญฆไผๆดๅฅฝ็ๆนๆณใ\n\nๆฟไฝ ๆฅๆๅๆฐใ\nๅฝไฝ ็ซๅจ้็็ๅฐๆนๆถ๏ผ\nๅฝไฝ ็ฌฌไธๆฌกไธพๆๅ่จๆถ๏ผ\nๅฝไฝ ้ๅฐๅฐ้พใๆๅฐๅฎณๆ็ๆถๅ๏ผ\nๅธๆไฝ ่ฝ่ฝป่ฝปๅฐๅ่ฏ่ชๅทฑ๏ผ\nโๆๅฏไปฅ่ฏไธ่ฏใโ\n\nๅฐฑ็ฎๆฒกๆไธๆฌกๆๅ๏ผไนๆฒกๆๅ
ณ็ณปใ\nๅคฑ่ดฅไธๆฏๅไบ๏ผ\nๅฎๅชๆฏๅ่ฏไฝ ๏ผไฝ ๆญฃๅจๅชๅใ\n\nๆๅธๆไฝ ๅญฆไผๅไบซๅฟซไนใ\nๆๅผๅฟ็ไบๆ
ๅ่ฏๅซไบบ๏ผ\nๆ็ฌๅฃฐ้็ป่บซ่พน็ไบบ๏ผ\nๅ ไธบๅฟซไน่ขซๅไบซ็ๆถๅ๏ผ\nไผๅๅพๆดๅคงใๆดไบฎใ\n\nๅฆๆๆไธๅคฉไฝ ๆๅฐ้พ่ฟ๏ผ\nๆๅธๆไฝ ็ฅ้โโ\n้พ่ฟๅนถไธไธข่ธ๏ผ\nๅญๆณฃไนไธๆฏ่ฝฏๅผฑใ\n\nๆฟไฝ ่ฝๆพๅฐไธไธชๅฎๅ
จ็ๅฐๆน๏ผ\nๆ
ขๆ
ขๆๅฟ้็่ฏ่ฏดๅบๆฅ๏ผ\n็ถๅๅไธๆฌกๆฌ่ตทๅคด๏ผ็่งๅธๆใ\n\nๆ่ฟๅธๆไฝ ่ฝๆฅๆๆขฆๆณใ\n่ฟไธชๆขฆๆณไน่ฎธๅพๅคง๏ผ\nไน่ฎธๅพๅฐ๏ผ\nไน่ฎธ็ฐๅจ่ฟ่ฏดไธๆธ
ๆฅใ\n\nๆฒกๅ
ณ็ณปใ\nๆขฆๆณไผๅไฝ ไธ่ตท้ฟๅคง๏ผ\nๅจๆถ้ด้ๆ
ขๆ
ขๅๅพๆธ
ๆฅใ\n\nๆๅ๏ผๆๆณ้ไฝ ไธไธชๆๆ้่ฆ็็ฅ็ฆ๏ผ\n\nๆฟไฝ ่ขซไธ็ๆธฉๆๅฏนๅพ
๏ผ\nไนๆฟไฝ ๆไธบไธไธชๆธฉๆ็ไบบใ\n\nๆฟไฝ ็ๆฏไธๅคฉ๏ผ\n้ฝๅผๅพ่ขซ่ฎฐไฝ๏ผ\n้ฝๅผๅพ่ขซ็ๆใ\n\nไบฒ็ฑ็ไฝ ๏ผ\n่ฏท่ฎฐไฝ๏ผ\nไฝ ๆฏ็ฌไธๆ ไบ็๏ผ\nไฝ ๅทฒ็ปๅพๆฃไบ๏ผ\n่ไฝ ็ๆชๆฅ๏ผ\nไธๅฎไผๆ
ขๆ
ขๅๅพ้ช้ชๅๅ
ใ\n\n็ฅไฝ ๅฅๅบทใๅๆขใๅนธ็ฆ๏ผ\n็ฅไฝ ๆฐธ่ฟๅธฆ็็ฌๅฎนๅๅ่ตฐใ"text_2 = "We stand on the threshold of the AI era.\nArtificial intelligence is no longer just a concept in laboratories, but is entering every industry, every creative endeavor, and every decision. It has learned to see, hear, speak, and think, and is beginning to become an extension of human capabilities. AI is not about replacing humans, but about amplifying human creativity, making knowledge more equitable, more efficient, and allowing imagination to reach further. A new era, jointly shaped by humans and intelligent systems, has arrived."text_3 = "nin2 hao3๏ผqing3 wen4 nin2 lai2 zi4 na3 zuo4 cheng2 shi4๏ผ"text_4 = "nin2 hao3๏ผqing4 wen3 nin2 lai2 zi4 na4 zuo3 cheng4 shi3๏ผ"text_5 = "ๆจๅฅฝ๏ผ่ฏท้ฎๆจๆฅ่ชๅช zuo4 cheng2 shi4๏ผ"text_6 = "/hษloส, meษช aษช รฆsk wษชtส sษชti juห ษหr frสm?/"text_7 = "Bonjour, je voudrais essayer une voix franรงaise naturelle et stable."text_8 = "ๆไปๅคฉๅญฆไน ไบไธ้ฆไธญๅฝ็ๅค่ฏ๏ผๅฎ็ๅๅญๆฏ[pause 3.2s]้ๅคๆ๏ผ"
# Use audio from ./assets/audio to avoid downloading from the cloud.ref_audio_1 = "https://speech-demo.oss-cn-shanghai.aliyuncs.com/moss_tts_demo/tts_readme_demo/reference_zh.wav"ref_audio_2 = "https://speech-demo.oss-cn-shanghai.aliyuncs.com/moss_tts_demo/tts_readme_demo/reference_en.m4a"
conversations = [ # Direct TTS (no reference). Language tags are recommended in v1.5. [processor.build_user_message(text=text_1)], [processor.build_user_message(text=text_2)], # Direct TTS (no reference). For languages โโother than Chinese and English, it is recommended to use language tags. [processor.build_user_message(text=text_7, language="French")], # Pinyin or IPA input [processor.build_user_message(text=text_3)], [processor.build_user_message(text=text_4)], [processor.build_user_message(text=text_5)], [processor.build_user_message(text=text_6)], # Explicit pause control. Use [pause X.Ys], such as [pause 3.2s]. [processor.build_user_message(text=text_8)], # Voice cloning (with reference) [processor.build_user_message(text=text_1, reference=[ref_audio_1])], [processor.build_user_message(text=text_2, reference=[ref_audio_2])], # Duration control [processor.build_user_message(text=text_2, tokens=325)], [processor.build_user_message(text=text_2, tokens=600)],]
model = AutoModel.from_pretrained( pretrained_model_name_or_path, trust_remote_code=True, # If FlashAttention 2 is installed, you can set attn_implementation="flash_attention_2" attn_implementation=attn_implementation, torch_dtype=dtype,).to(device)model.eval()
batch_size = 1
save_dir = Path("inference_root")save_dir.mkdir(exist_ok=True, parents=True)sample_idx = 0with torch.no_grad(): for start in range(0, len(conversations), batch_size): batch_conversations = conversations[start : start + batch_size] batch = processor(batch_conversations, mode="generation") input_ids = batch["input_ids"].to(device) attention_mask = batch["attention_mask"].to(device)
outputs = model.generate( input_ids=input_ids, attention_mask=attention_mask, max_new_tokens=4096, )
for message in processor.decode(outputs): audio = message.audio_codes_list[0] out_path = save_dir / f"sample{sample_idx}.wav" sample_idx += 1 torchaudio.save(out_path, audio.unsqueeze(0), processor.model_config.sampling_rate)