Add language/base_model metadata to model card

README.md

@@ -1,6 +1,10 @@
 ---
 license: apache-2.0
+language:
+- es
 library_name: onnx-asr
+base_model:
+- BSC-LT/stt_los_conformer_transducer_large_punctuated
 tags:
 - automatic-speech-recognition
 - onnx
@@ -10,24 +14,15 @@ pipeline_tag: automatic-speech-recognition
 
 # bsc-lt-los-conformer-transducer-large-punctuated-onnx
 
-NVIDIA NeMo ASR model exported to ONNX for the
+ASR model exported to ONNX for the
 [onnx-asr](https://github.com/istupakov/onnx-asr) library and the
 [ovos-stt-plugin-onnx-asr](https://github.com/OpenVoiceOS/ovos-stt-plugin-onnx-asr)
-OpenVoiceOS STT plugin.
+OpenVoiceOS STT plugin. Ships both fp32 and int8 weights.
 
-Converted from [BSC-LT/stt_los_conformer_transducer_large_punctuated](https://huggingface.co/BSC-LT/stt_los_conformer_transducer_large_punctuated) (apache-2.0).
-Decoder: RNN-T Transducer (`encoder-model.onnx` + `decoder_joint-model.onnx`) — `model_type: nemo-conformer-rnnt`, features_size 80,
-subsampling_factor 4.
+Language: **Spanish**. Converted from [BSC-LT/stt_los_conformer_transducer_large_punctuated](https://huggingface.co/BSC-LT/stt_los_conformer_transducer_large_punctuated).
 
 ```python
 import onnx_asr
 model = onnx_asr.load_model("OpenVoiceOS/bsc-lt-los-conformer-transducer-large-punctuated-onnx")
 print(model.recognize("audio.wav"))
 ```
-
-Or via OpenVoiceOS config:
-
-```json
-{"stt": {"module": "ovos-stt-plugin-onnx-asr",
-         "ovos-stt-plugin-onnx-asr": {"model": "OpenVoiceOS/bsc-lt-los-conformer-transducer-large-punctuated-onnx"}}}
-```