Spark-TTS is an efficient text-to-speech system based on large language models (LLM), supporting bilingual synthesis in Chinese and English with zero-shot voice cloning.

Audio ProcessingSafetensorsMultiple Languages

This is a text-to-speech model based on the MLX format, supporting both English and Chinese, converted from prince-canuma/Spark-TTS-0.5B.

Audio ProcessingSafetensorsMultiple Languages

Spark-TTS-0.5B-4-6bit is a text-to-speech model based on the MLX format, supporting both English and Chinese.

Audio ProcessingSafetensorsMultiple Languages

Spark-TTS-0.5B-fp16 is a text-to-speech model based on the MLX format, supporting both English and Chinese.

Audio ProcessingSafetensorsMultiple Languages

Spark-TTS is an advanced text-to-speech system based on large language models, capable of high-precision and natural-sounding speech synthesis.

Audio ProcessingSafetensorsMultiple Languages

Spark-TTS is an advanced text-to-speech system that leverages the powerful capabilities of large language models (LLMs) to achieve highly accurate and naturally fluent speech synthesis.

Audio ProcessingSafetensors

SPARK.Chroma is a text-to-image generation model fine-tuned based on the Chroma1-HD model, focusing on generating realistic images. This model has 8.9 billion parameters, uses the Apache 2.0 license agreement, and is currently in the preview version.

Computer VisionDiffusersEnglish

Spark-TTS is an advanced text-to-speech system that leverages the powerful capabilities of large language models (LLMs) to achieve high-precision and natural-sounding speech synthesis.

Audio ProcessingSafetensors

Rain's SQLCoder is an advanced large language model specifically designed for converting natural language to SparkSQL, fine-tuned from Qwen2.5-Coder-32B-Instruct with 32 billion parameters.

Natural Language ProcessingTransformers

A text-to-video model fine-tuned on the 3dgs-dissolve dataset based on THUDM/CogVideoX-5b, specializing in 3D object dissolution and spark effect generation

MultimodalDiffusers

Qwen2.5-14B Aletheia v1 is a hybrid model specifically designed for role-playing and story creation, fused from the Sugarquill and Neon models. It combines the creative spark of Sugarquill with the ease of guidance of Neon, suitable for various creative writing and role-playing scenarios.

Natural Language ProcessingTransformersEnglish

SPARK-mini-instruct is an instruction-tuned version based on SPARK-mini-base, a 3.8-billion-parameter language model specifically trained for tasks in the nuclear power domain.

Natural Language ProcessingTransformersEnglish

A LongT5-XL model fine-tuned on the BookSum dataset, specifically designed for long-text summarization, capable of generating SparkNotes-like summaries.

Natural Language ProcessingTransformers

DialogRPT-depth is a dialogue response ranking model developed by Microsoft Research, focusing on predicting the likelihood of dialogue responses sparking long discussion threads.

Natural Language ProcessingTransformers

A large-scale summarization model based on the PEGASUS architecture, fine-tuned on the booksum dataset, excels at generating easy-to-understand SparkNotes-style summaries

Natural Language ProcessingTransformersEnglish