---
language:
- zh
- en
pipeline_tag: text-to-speech
license: other
license_name: component-specific
license_link: https://huggingface.co/rcell233/pl-flow/blob/main/THIRD_PARTY.md
tags:
- audio
- flow-matching
- safetensors
---

# PL-Flow pretrained bundle

Model weights for the PL-Flow two-stage speech synthesis implementation.
Licenses differ by component; see [THIRD_PARTY.md](THIRD_PARTY.md).

## Components

| Component | Function | Origin | Weight license |
| --- | --- | --- | --- |
| `s1` | Phoneme-aligned prosody flow, QK normalization | Trained from random initialization, EMA | [GPL-3.0-only](LICENSE) |
| `s2` | Duration-conditioned acoustic flow, QK normalization | Trained from random initialization, EMA | [GPL-3.0-only](LICENSE) |
| `aligner` | HuBERT/text forced alignment | Trained from random initialization | [GPL-3.0-only](LICENSE) |
| `vocoder` | 32 kHz mono, 32-channel 50 Hz SQ-GAN codec | Trained from random initialization, EMA | [GPL-3.0-only](LICENSE) |
| `plbert` | Frozen phoneme ALBERT | Extracted from Kokoro | [Apache-2.0](plbert/LICENSE) |
| `hubert` | Frozen semantic features | TencentGameMate Chinese HuBERT | [MIT](hubert/LICENSE) |
| `speaker` | Frozen WavLM/ECAPA speaker features | External checkpoint linked by Seed-TTS-Eval | [Download and upstream terms](speaker/NOTICE.md) |

Six components contain `config.json` and `model.safetensors`. The speaker directory
contains configuration and download instructions only. `bundle.json` pins SHA256
hashes, the external speaker download, the prosody-code interface and inference
settings.

## Usage

Install the PL-Flow source package in your own environment, then:

```bash
hf download rcell233/pl-flow --local-dir artifacts/pretrained
```

Download **[wavlm_large_finetune.pth](https://drive.google.com/file/d/1-aE1NfzpRCLxA4GUxX9ITI3F9LlbtEGP/view)**
from the model link in [Seed-TTS-Eval](https://github.com/BytedanceSpeech/seed-tts-eval#metrics)
and save it as `artifacts/pretrained/speaker/wavlm_large_finetune.pth`.
PL-Flow verifies the checkpoint's SHA256 and extracts speaker features
automatically during synthesis.

```bash
pl-flow verify --models artifacts/pretrained
pl-flow synthesize --models artifacts/pretrained \
  --reference-audio data/reference.wav --reference-text '这是参考音频的文本。' \
  --text '你好，欢迎使用语音合成。' --language zh --output outputs/example.wav
```

Default sampling uses S1 **8 Euler steps / CFG 2.1**, S2 **10 Euler steps / CFG
2.8**, temperature 1.0 and CUDA BF16 autocast for the flow models. Guidance is
`(1 + scale) * conditional - scale * unconditional`. Audio encoders and the codec
run in FP32. Context limits: 512 S1 tokens, 1024 total S2 frames, 250 prompt frames.

S1 and S2 use EMA weights. The bundle supports inference and initialization for
training. Resuming training requires a full training checkpoint. The ASR aligner
and SQ codec can also be trained using the PL-Flow package.