Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,9 @@ LLaMA-Omni is a speech-language model built upon Llama-3.1-8B-Instruct. It suppo
|
|
| 30 |
|
| 31 |
♻️ **Trained in less than 3 days using just 4 GPUs.**
|
| 32 |
|
|
|
|
|
|
|
|
|
|
| 33 |
## Install
|
| 34 |
|
| 35 |
1. Clone this repository.
|
|
@@ -99,6 +102,8 @@ python -m omni_speech.serve.model_worker --host 0.0.0.0 --controller http://loca
|
|
| 99 |
|
| 100 |
4. Visit [http://localhost:8000/](http://localhost:8000/) and interact with LLaMA-3.1-8B-Omni!
|
| 101 |
|
|
|
|
|
|
|
| 102 |
## Local Inference
|
| 103 |
|
| 104 |
To run inference locally, please organize the speech instruction files according to the format in the `omni_speech/infer/examples` directory, then refer to the following script.
|
|
|
|
| 30 |
|
| 31 |
♻️ **Trained in less than 3 days using just 4 GPUs.**
|
| 32 |
|
| 33 |
+
|
| 34 |
+
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/65b7573482d384513443875e/dr4XWUxzuVQ52lBuzNBTt.mp4"></video>
|
| 35 |
+
|
| 36 |
## Install
|
| 37 |
|
| 38 |
1. Clone this repository.
|
|
|
|
| 102 |
|
| 103 |
4. Visit [http://localhost:8000/](http://localhost:8000/) and interact with LLaMA-3.1-8B-Omni!
|
| 104 |
|
| 105 |
+
**Note: Due to the instability of streaming audio playback in Gradio, we have only implemented streaming audio synthesis without enabling autoplay. If you have a good solution, feel free to submit a PR. Thanks!**
|
| 106 |
+
|
| 107 |
## Local Inference
|
| 108 |
|
| 109 |
To run inference locally, please organize the speech instruction files according to the format in the `omni_speech/infer/examples` directory, then refer to the following script.
|