Added small description
Browse files
README.md
CHANGED
|
@@ -1,3 +1,43 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- uk
|
| 4 |
+
library_name: nemo
|
| 5 |
+
datasets:
|
| 6 |
+
- mozilla-foundation/common_voice_10_0
|
| 7 |
+
- Yehor/ukrainian-tts-mykyta
|
| 8 |
+
- Yehor/ukrainian-tts-lada
|
| 9 |
+
- Yehor/ukrainian-tts-tetiana
|
| 10 |
+
tags:
|
| 11 |
+
- automatic-speech-recognition
|
| 12 |
+
model-index:
|
| 13 |
+
- name: stt_ua_fastconformer_hybrid_large_pc
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Mozilla Common Voice 10.0
|
| 20 |
+
type: mozilla-foundation/common_voice_10_0
|
| 21 |
+
config: clean
|
| 22 |
+
split: test
|
| 23 |
+
args:
|
| 24 |
+
language: uk
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Test WER
|
| 27 |
+
type: wer
|
| 28 |
+
value: 7.07
|
| 29 |
license: mit
|
| 30 |
---
|
| 31 |
+
# FastConformer Hybrid Transducer-CTC Large P&C (uk-UA)
|
| 32 |
+
|
| 33 |
+
<style>
|
| 34 |
+
img {
|
| 35 |
+
display: inline;
|
| 36 |
+
}
|
| 37 |
+
</style>
|
| 38 |
+
|
| 39 |
+
| [](#model-architecture)
|
| 40 |
+
| [](#model-architecture)
|
| 41 |
+
| [](#datasets) |
|
| 42 |
+
## Attribution
|
| 43 |
+
As initial checkpoint used [stt_ua_fastconformer_hybrid_large_pc](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_ua_fastconformer_hybrid_large_pc) by [NVIDIA](https://github.com/NVIDIA) licensed under [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
|