update metadata
Browse files
README.md
CHANGED
|
@@ -1,3 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
## <span style="color:#ffb300;">🐤 Canary 1B v2: Multitask Speech Transcription and Translation Model </span>
|
| 2 |
|
| 3 |
## <span style="color:#b37800;">Description</span>
|
|
@@ -456,4 +505,4 @@ Model and dataset restrictions | The Principle of least privilege (P
|
|
| 456 |
|
| 457 |
\[15] [Speech Recognition and Multi-Speaker Diarization of Long Conversations](https://arxiv.org/abs/2005.08072)
|
| 458 |
|
| 459 |
-
\[16] [MUSAN: A Music, Speech, and Noise Corpus](https://arxiv.org/abs/1510.08484)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- nvidia/Granary
|
| 5 |
+
- librispeech_asr
|
| 6 |
+
- fisher_corpus
|
| 7 |
+
- Switchboard-1
|
| 8 |
+
- WSJ-0
|
| 9 |
+
- WSJ-1
|
| 10 |
+
- vctk
|
| 11 |
+
- voxpopuli
|
| 12 |
+
- europarl
|
| 13 |
+
- multilingual_librispeech
|
| 14 |
+
- mozilla-foundation/common_voice_8_0
|
| 15 |
+
- MLCommons/peoples_speech
|
| 16 |
+
- google/fleurs
|
| 17 |
+
language:
|
| 18 |
+
- bg
|
| 19 |
+
- hr
|
| 20 |
+
- cs
|
| 21 |
+
- da
|
| 22 |
+
- nl
|
| 23 |
+
- en
|
| 24 |
+
- et
|
| 25 |
+
- fi
|
| 26 |
+
- fr
|
| 27 |
+
- de
|
| 28 |
+
- el
|
| 29 |
+
- hu
|
| 30 |
+
- it
|
| 31 |
+
- lv
|
| 32 |
+
- lt
|
| 33 |
+
- mt
|
| 34 |
+
- pl
|
| 35 |
+
- pt
|
| 36 |
+
- ro
|
| 37 |
+
- sk
|
| 38 |
+
- sl
|
| 39 |
+
- es
|
| 40 |
+
- sv
|
| 41 |
+
- ru
|
| 42 |
+
- uk
|
| 43 |
+
metrics:
|
| 44 |
+
- bleu
|
| 45 |
+
- wer
|
| 46 |
+
- comet
|
| 47 |
+
pipeline_tag: automatic-speech-recognition
|
| 48 |
+
library_name: nemo
|
| 49 |
+
---
|
| 50 |
## <span style="color:#ffb300;">🐤 Canary 1B v2: Multitask Speech Transcription and Translation Model </span>
|
| 51 |
|
| 52 |
## <span style="color:#b37800;">Description</span>
|
|
|
|
| 505 |
|
| 506 |
\[15] [Speech Recognition and Multi-Speaker Diarization of Long Conversations](https://arxiv.org/abs/2005.08072)
|
| 507 |
|
| 508 |
+
\[16] [MUSAN: A Music, Speech, and Noise Corpus](https://arxiv.org/abs/1510.08484)
|