Update README.md
Browse files
README.md
CHANGED
|
@@ -57,6 +57,8 @@ model-index:
|
|
| 57 |
|
| 58 |
# SpeechLLM
|
| 59 |
|
|
|
|
|
|
|
| 60 |
SpeechLLM is a multi-modal LLM trained to predict the metadata of the speaker's turn in a conversation. SpeechLLM model is based on HubertX acoustic encoder and TinyLlama LLM. The model predicts the following:
|
| 61 |
1. **SpeechActivity** : if the audio signal contains speech (True/False)
|
| 62 |
2. **Transcript** : ASR transcript of the audio
|
|
|
|
| 57 |
|
| 58 |
# SpeechLLM
|
| 59 |
|
| 60 |
+
[The model is still training, we will be releasing the latest checkpoints soon...]
|
| 61 |
+
|
| 62 |
SpeechLLM is a multi-modal LLM trained to predict the metadata of the speaker's turn in a conversation. SpeechLLM model is based on HubertX acoustic encoder and TinyLlama LLM. The model predicts the following:
|
| 63 |
1. **SpeechActivity** : if the audio signal contains speech (True/False)
|
| 64 |
2. **Transcript** : ASR transcript of the audio
|