Update README.md
Browse files
README.md
CHANGED
|
@@ -78,6 +78,10 @@ model-index:
|
|
| 78 |
|
| 79 |
# SpeechLLM
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
|
| 82 |
|
| 83 |
SpeechLLM is a multi-modal LLM trained to predict the metadata of the speaker's turn in a conversation. speechllm-2B model is based on HubertX audio encoder and TinyLlama LLM. The model predicts the following:
|
|
|
|
| 78 |
|
| 79 |
# SpeechLLM
|
| 80 |
|
| 81 |
+
[](https://github.com/skit-ai/SpeechLLM.git)
|
| 82 |
+
[](https://colab.research.google.com/drive/1uqhRl36LJKA4IxnrhplLMv0wQ_f3OuBM?usp=sharing)
|
| 83 |
+
|
| 84 |
+
|
| 85 |
|
| 86 |
|
| 87 |
SpeechLLM is a multi-modal LLM trained to predict the metadata of the speaker's turn in a conversation. speechllm-2B model is based on HubertX audio encoder and TinyLlama LLM. The model predicts the following:
|