DirectS2ST / README.md
TedZhangHao's picture
DirectS2ST checkpoints
5f986ca
|
Raw History Blame Contribute Delete
1.85 kB
---
tags:
- speech-to-speech-translation
- expressive-speech-translation
- mimi
language:
- en
- de
- es
---
# DirectS2ST
Checkpoints of DirectS2ST, the end-to-end expressive speech-to-speech translation
model from *Holistic Parallel Supervision for Expressive Speech-to-Speech
Translation*, trained on VC-Dub (professional dubbing + multilingual voice
conversion).
| Folder | Direction |
| --- | --- |
| `en-de/` | English → German |
| `en-es/` | English → Spanish |
Each folder holds `pytorch_model.bin`, `model_config.json` and the
SentencePiece-8k text tokenizer (`text_tokenizer/`).
Given English source speech, the model predicts all 16 Mimi codec streams of
the target speech directly: a frozen w2v-BERT 2.0 encoder, an AR temporal
decoder (source text, target text and codec stream c0 with one shared head), and
an NAR depth decoder (c1-c15) conditioned on a CAMPPlus speaker prefix and a
source codec prompt.
## Usage
Code, setup and training: <https://github.com/hzted/truly-e2e-expressive-s2st-demo/tree/main/DirectS2ST>
```
hf download TedZhangHao/DirectS2ST --include "en-es/*" --local-dir checkpoints
python inference/infer.py \
--checkpoint-dir checkpoints/en-es \
--campplus-model-root /path/to/seed-vc \
--campplus-checkpoint-path /path/to/campplus_cn_en_common.pt \
--source-wav input_en.wav --output-wav output_es.wav
```
Demo: <https://hzted.github.io/truly-e2e-expressive-s2st-demo/>
## Third-party components
The checkpoints contain the frozen weights of
[w2v-BERT 2.0](https://huggingface.co/facebook/w2v-bert-2.0) and
[Mimi](https://huggingface.co/kyutai/mimi); their licenses apply to those
parts. The CAMPPlus speaker encoder
([iic/speech_campplus_sv_zh_en_16k-common_advanced](https://modelscope.cn/models/iic/speech_campplus_sv_zh_en_16k-common_advanced))
is not included and is loaded at run time.