Text-to-Speech
Transformers
Safetensors
moss_tts_delay
feature-extraction
audio
cpu-optimized
custom_code
Instructions to use daksh-neo/Moss_tts_cpu_optimised with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use daksh-neo/Moss_tts_cpu_optimised with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="daksh-neo/Moss_tts_cpu_optimised", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("daksh-neo/Moss_tts_cpu_optimised", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download chat_template.jinja from daksh-neo/Moss_tts_cpu_optimised: direct link, hf CLI and curl.
- Browser
- Download file 352 Bytes
-
https://huggingface.co/daksh-neo/Moss_tts_cpu_optimised/resolve/main/chat_template.jinja
- Command line
-
hf download hf://daksh-neo/Moss_tts_cpu_optimised/chat_template.jinja
-
curl -L -o chat_template.jinja https://huggingface.co/daksh-neo/Moss_tts_cpu_optimised/resolve/main/chat_template.jinja
352 Bytes
| {% for message in messages %}<|im_start|>{{ message['role'] }} | |
| {% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content.get('type') == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}<|im_end|> | |
| {% endfor %}{% if add_generation_prompt %}<|im_start|>assistant | |
| {% endif %} |