Text-to-Speech
Transformers
Safetensors
English
emosphere_pp
feature-extraction
emotional-tts
zero-shot-tts
flow-matching
emosphere
custom_code
Instructions to use RetentionLabs/EmoSphere-PP-16kHz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RetentionLabs/EmoSphere-PP-16kHz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="RetentionLabs/EmoSphere-PP-16kHz", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RetentionLabs/EmoSphere-PP-16kHz", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
13 days ago
-
Mixed float32 and float16 weights without NVFP4, and a new model card
Verified signature4be7049
18 days ago
-
docs(model): specify evaluator precision and bounded repeatability
Verified signaturefa72cc2 -
docs(model): report matched full ESD benchmark and paired uncertainty
Verified signature40d6c52 -
feat(model): stage static H64 NVFP4 and BF16 candidate for private validation
Verified signaturePrivate preflight of 42 CFM linears. Matched full1500 quality review remains pending. Packed weights are fixed; no QAT. The internal BF16 BigVGAN stays pinned to the frozen benchmark revision.39f692e
19 days ago
-
Stage selective MSE PTQ candidate with exact export verification, restoration pending
Verified signature427f634 -
Use 16kHz in the model name and loading examples
Verified signatureb011281 -
Release GPTQ calibrated NVFP4 weights and processor
Verified signature2f05e3a -
initial commit
Verified signature0b31cc5