Skip to content
ModelListedExternal
Browse files

Fish Audio S2 Pro MLX FP16

This is an fp16 artifact export of fishaudio/s2-pro for Apple Silicon runtime evaluation.

Sourcehuggingface.co/aufklarer/Fish-Audio-S2-Pro-MLX-fp16/tree/254339851f9f39b68d06cc9284addab5fb32be13
KindOtherBase modelfishaudio/s2-proVersionRevision 2543398Unratedgrade

Model source

Kind
Other
File size
1.01–4.64 GB
Base model
fishaudio/s2-pro
Version
vRevision 2543398
Updated
Nov 6, 2026
Downloads
66
Source
Hugging Face

Source description

Fish-Audio-S2-Pro-MLX-fp16

This is an fp16 artifact export of fishaudio/s2-pro for Apple Silicon runtime evaluation.

Runtime support is not implied by this model card. The bundle preserves upstream key names and is intended for a speech-swift Swift/MLX port.

Model

FieldValue
Sourcefishaudio/s2-pro
Source revision1de9996b6be38b745688de084d87a5633f714e4e
FormatMLX fp16 safetensors
License postureresearch/non-commercial
Readinessbenchmark-only
Sample rateSee upstream/runtime implementation.
Voice conditioningFish Speech reference / speaker conditioning stack
Runtime statusbenchmark artifact; not for default product integration

Emotion Control

FieldValue
Marker syntaxfree-form inline bracket tags
Supported markers[pause], [emphasis], [laughing], [excited], [angry], [whisper], [screaming], [shouting], [surprised], [sad]

Files

  • config.json - root config for Hugging Face download tracking and runtime metadata
  • soniqo_manifest.json - export manifest with source, marker, readiness, and file metadata
  • *.safetensors - fp16-converted model weights with upstream key names preserved

Notes

  • Strong benchmark for free-form inline prosody/emotion tags.
  • Public weights are research/non-commercial; commercial use requires a separate license.
  • The codec checkpoint is converted from PyTorch pickle to safetensors when this model is exported.

Usage

These artifacts are for runtime implementation and evaluation. They are not a drop-in Transformers checkpoint.

git clone https://huggingface.co/aufklarer/Fish-Audio-S2-Pro-MLX-fp16

Source

Links

Sources

1 source
Hugging FacePrimaryVersion 254339851f9f39b68d06cc9284addab5fb32be13
huggingface.co/aufklarer/Fish-Audio-S2-Pro-MLX-fp16/tree/254339851f9f39b68d06cc9284addab5fb32be13

Verified Nov 6

Download files

Model · 2 weight files

All files listed in the provider index are present.

Repository files

File inventory only; completeness is unverified.

Model artifacts

3 artifacts

codec.safetensors

safetensors · FP16 + BOOL (tensor header) · 1.01 GB · SHA-256 26da752caffb…37ae · Hugging Face

Download file

model-00001-of-00002.safetensors

safetensors · 4.64 GB · SHA-256 a294a9dbd8d8…07c9 · Hugging Face

Download shard

model-00002-of-00002.safetensors

safetensors · 3.85 GB · SHA-256 5aa74fa39e64…c03b · Hugging Face

Download shard

Source excerpts

3 excerpts
ReadmeAug 29huggingface.co/aufklarer/Fish-Audio-S2-Pro-MLX-fp16

--- license: other language: - hi - en - zh - ja - ko - es - pt - ar - ru - fr - de tags: - text-to-speech - hindi - emotion-control - fish-audio - benchmark - mlx - fp16 base_model: fishaudio/s2-pro library_name: mlx pipeline_tag: text-to-speech --- # Fish-Audio-S2-Pro-MLX-fp16 This is an fp16 artifact export of [fishaudio/s2-pro](https://huggingface.co/fishaudio/s2-pro) for Apple Silicon runtime evaluation. Runtime support is not implied by this model card. The bundle preserves upstream key names and is intended for a `speech-swift` Swift/MLX port. ## Model | Field | Value | |---|---| | Source | `fishaudio/s2-pro` | | Source revision | `1de9996b6be38b745688de084d87a5633f714e4e` | | Format | MLX fp16 safetensors | | License posture | research/non-commercial | | Readiness | benchmark-only | | Sample rate | See upstream/runtime implementation. | | Voice conditioning | Fish Speech reference / speaker conditioning stack | | Runtime status | benchmark artifact; not for default product integration | ## Emotion Control | Field | Value | |---|---| | Marker syntax | free-form inline bracket tags | | Supported markers | `[pause]`, `[emphasis]`, `[laughing]`, `[excited]`, `[angry]`, `[whisper]`, `[screaming]`, `[shouting]`, `[surprised]`, `[sad]` | ## Files - `config.json` - root config for Hugging Face download tracking and runtime metadata - `soniqo_manifest.json` - export manifest with source, marker, readiness, and file metadata - `*.safetensors` - fp16-converted model weights with upstream key names preserved ## Notes - Strong benchmark for free-form inline prosody/emotion tags. - Public weights are research/non-commercial; commercial use requires a separate license. - The codec checkpoint is converted from PyTorch pickle to safetensors when this model is exported. ## Usage These artifacts are for runtime implementation and evaluation. They are not a drop-in Transformers checkpoint. ```bash git clone https://huggingface.co/aufklarer/Fish-Audio-S2-Pro-MLX-fp16 ``` ## Source - Upstream model: https://huggingface.co/fishaudio/s2-pro ## Links - [speech-swift](https://github.com/soniqo/speech-swift) - Apple SDK - [Speech Studio](https://soniqo.audio/speech-studio) - local speech generation and voice cloning app - [Docs](https://soniqo.audio/getting-started) - install and CLI docs - [soniqo.audio](https://soniqo.audio) - website - [Blog](https://so...

NoteNov 6huggingface.co/aufklarer/Fish-Audio-S2-Pro-MLX-fp16

Source context: 66 downloads · 1 likes · Pipeline text-to-speech · Library mlx · Repo aufklarer/Fish-Audio-S2-Pro-MLX-fp16

NoteAug 29huggingface.co/aufklarer/Fish-Audio-S2-Pro-MLX-fp16

Source context: 86 downloads · 1 likes · Pipeline text-to-speech · Library mlx · Repo aufklarer/Fish-Audio-S2-Pro-MLX-fp16