Add pipeline tag and library name
Browse filesThis PR adds the `pipeline_tag` and `library_name` to the model card metadata. The `pipeline_tag` is set to `audio-text-to-text` reflecting the model's capabilities as described in the paper. The `library_name` is set to `transformers` as indicated by the usage example in the Github README.
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
Spire is a 7B parameter decoder-only model with strong abilities in machine translation, automatic speech recognition, and speech translation. [SpireBase](https://huggingface.co/utter-project/SpireBase) was created by applying speech-centric continued pretraining to [TowerBase-7B-v0.1](https://huggingface.co/Unbabel/TowerBase-7B-v0.1), which was itself created by applying continued pretraining to [Llama 2](https://huggingface.co/meta-llama/Llama-2-7b).
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
+
pipeline_tag: audio-text-to-text
|
| 4 |
+
library_name: transformers
|
| 5 |
---
|
| 6 |
|
| 7 |
Spire is a 7B parameter decoder-only model with strong abilities in machine translation, automatic speech recognition, and speech translation. [SpireBase](https://huggingface.co/utter-project/SpireBase) was created by applying speech-centric continued pretraining to [TowerBase-7B-v0.1](https://huggingface.co/Unbabel/TowerBase-7B-v0.1), which was itself created by applying continued pretraining to [Llama 2](https://huggingface.co/meta-llama/Llama-2-7b).
|