Instructions to use OpenVoiceOS/dolphin-small-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use OpenVoiceOS/dolphin-small-onnx with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "OpenVoiceOS/dolphin-small-onnx" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Language and region are predicted when no language is given
Browse files
README.md
CHANGED
|
@@ -98,7 +98,7 @@ model = onnx_asr.load_model("OpenVoiceOS/dolphin-small-onnx", quantization="int8
|
|
| 98 |
|
| 99 |
The `language` argument accepts a full tag (`zh-CN`), the same tag with an underscore
|
| 100 |
(`zh_CN`) or a bare language (`zh`), which maps to the first region of that language.
|
| 101 |
-
Leave `language` out and the model
|
| 102 |
|
| 103 |
## Languages
|
| 104 |
|
|
|
|
| 98 |
|
| 99 |
The `language` argument accepts a full tag (`zh-CN`), the same tag with an underscore
|
| 100 |
(`zh_CN`) or a bare language (`zh`), which maps to the first region of that language.
|
| 101 |
+
Leave `language` out and the model predicts the language and the region itself.
|
| 102 |
|
| 103 |
## Languages
|
| 104 |
|