Instructions to use zenlm/zen-translator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen-translator with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="zenlm/zen-translator")# pip install -U transformers accelerate # Load model directly from transformers import ZenTranslatorForSpeechTranslation model = ZenTranslatorForSpeechTranslation.from_pretrained("zenlm/zen-translator", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Neutralize remaining upstream directory name reference
Browse files
README.md
CHANGED
|
@@ -53,7 +53,7 @@ tags:
|
|
| 53 |
| `llm.pt` | Language model backbone | ~1.25B params |
|
| 54 |
| `flow.pt` | Acoustic flow matching model | ~420M params |
|
| 55 |
| `hift.pt` | High-fidelity vocoder | ~82M params |
|
| 56 |
-
| `CosyVoice-BlankEN/
|
| 57 |
| `model_config.yaml` (cosyvoice2.yaml) | Full model configuration | Audio pipeline config |
|
| 58 |
|
| 59 |
## Package Structure
|
|
|
|
| 53 |
| `llm.pt` | Language model backbone | ~1.25B params |
|
| 54 |
| `flow.pt` | Acoustic flow matching model | ~420M params |
|
| 55 |
| `hift.pt` | High-fidelity vocoder | ~82M params |
|
| 56 |
+
| `voice-en/` (CosyVoice-BlankEN/) | English voice reference data | Tokenizer + vocab |
|
| 57 |
| `model_config.yaml` (cosyvoice2.yaml) | Full model configuration | Audio pipeline config |
|
| 58 |
|
| 59 |
## Package Structure
|