Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- et
|
| 5 |
+
pipeline_tag: automatic-speech-recognition
|
| 6 |
+
---
|
| 7 |
+
This model is ONNX version of an Icefall Zipformer streaming ASR model for Estonian. It is identical in training details to https://huggingface.co/TalTechNLP/streaming-zipformer-large.et-en,
|
| 8 |
+
but it's trained on transcript where number expressions are converted from words to digits.
|
| 9 |
+
|
| 10 |
+
Note that it tends to struggle with more complex numerical expressions (exceeding four digits).
|
| 11 |
+
|
| 12 |
+
Use sherpa-onnx to do ASR:
|
| 13 |
+
|
| 14 |
+
E.g., under Linux, using card 3 as input device:
|