Hugging Face's logo

OpenMOSS-Team
/
MOSS-SoundEffect

Text-to-Audio
Safetensors
moss_tts_delay
custom_code
Model card Files
xet
Community
YWMditto commited on
Commit
60478e8
·
1 Parent(s): f78017d

update readme

Browse files
Files changed (1) hide show
  1. README.md +44 -6
README.md CHANGED
@@ -26,12 +26,12 @@ When a single piece of audio needs to **sound like a real person**, **pronounce
26
 
27
  | Model | Architecture | Size | Model Card | Hugging Face |
28
  |---|---|---:|---|---|
29
- | **MOSS-TTS** | MossTTSDelay | 8B | [moss_tts_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/moss_tts_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS) |
30
- | | MossTTSLocal | 1.7B | [moss_tts_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/moss_tts_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Local-Transformer) |
31
- | **MOSS‑TTSD‑V1.0** | MossTTSDelay | 8B | [moss_ttsd_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/moss_ttsd_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTSD-v1.0) |
32
- | **MOSS‑VoiceGenerator** | MossTTSDelay | 1.7B | [moss_voice_generator_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/moss_voice_generator_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-Voice-Generator) |
33
- | **MOSS‑SoundEffect** | MossTTSDelay | 8B | [moss_sound_effect_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/moss_sound_effect_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-SoundEffect) |
34
- | **MOSS‑TTS‑Realtime** | MossTTSRealtime | 1.7B | [moss_tts_realtime_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/moss_tts_realtime_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Realtime) |
35
 
36
 
37
  # MOSS-SoundEffect
@@ -81,6 +81,44 @@ MOSS‑SoundEffect focuses on **contextual audio completion** beyond speech, ena
81
  ## 2. Quick Start
82
 
83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
 
85
  ```python
86
  import os
 
26
 
27
  | Model | Architecture | Size | Model Card | Hugging Face |
28
  |---|---|---:|---|---|
29
+ | **MOSS-TTS** | MossTTSDelay | 8B | [moss_tts_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_tts_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS) |
30
+ | | MossTTSLocal | 1.7B | [moss_tts_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_tts_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Local-Transformer) |
31
+ | **MOSS‑TTSD‑V1.0** | MossTTSDelay | 8B | [moss_ttsd_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_ttsd_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTSD-v1.0) |
32
+ | **MOSS‑VoiceGenerator** | MossTTSDelay | 1.7B | [moss_voice_generator_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_voice_generator_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-Voice-Generator) |
33
+ | **MOSS‑SoundEffect** | MossTTSDelay | 8B | [moss_sound_effect_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_sound_effect_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-SoundEffect) |
34
+ | **MOSS‑TTS‑Realtime** | MossTTSRealtime | 1.7B | [moss_tts_realtime_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_tts_realtime_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Realtime) |
35
 
36
 
37
  # MOSS-SoundEffect
 
81
  ## 2. Quick Start
82
 
83
 
84
+ ### Environment Setup
85
+
86
+ We recommend a clean, isolated Python environment with **Transformers 5.0.0** to avoid dependency conflicts.
87
+
88
+ ```bash
89
+ conda create -n moss-tts python=3.12 -y
90
+ conda activate moss-tts
91
+ ```
92
+
93
+ Install all required dependencies:
94
+
95
+ ```bash
96
+ git clone https://github.com/OpenMOSS/MOSS-TTS.git
97
+ cd MOSS-TTS
98
+ pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e .
99
+ ```
100
+
101
+ #### (Optional) Install FlashAttention 2
102
+
103
+ For better speed and lower GPU memory usage, you can install FlashAttention 2 if your hardware supports it.
104
+
105
+ ```bash
106
+ pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[flash-attn]"
107
+ ```
108
+
109
+ If your machine has limited RAM and many CPU cores, you can cap build parallelism:
110
+
111
+ ```bash
112
+ MAX_JOBS=4 pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[flash-attn]"
113
+ ```
114
+
115
+ Notes:
116
+ - Dependencies are managed in `pyproject.toml`, which currently pins `torch==2.9.1+cu128` and `torchaudio==2.9.1+cu128`.
117
+ - If FlashAttention 2 fails to build on your machine, you can skip it and use the default attention backend.
118
+ - FlashAttention 2 is only available on supported GPUs and is typically used with `torch.float16` or `torch.bfloat16`.
119
+
120
+
121
+ ### Basic Usage
122
 
123
  ```python
124
  import os