khanhld3
commited on
Commit
·
589548f
1
Parent(s):
c722643
[test] init
Browse files
README.md
CHANGED
|
@@ -31,40 +31,40 @@ tags:
|
|
| 31 |
license: cc-by-nc-4.0
|
| 32 |
model-index:
|
| 33 |
- name: ChunkFormer Large Vietnamese
|
| 34 |
-
results:
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
dataset:
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
metrics:
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
dataset:
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
metrics:
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
dataset:
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
metrics:
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
---
|
| 69 |
|
| 70 |
# **ChunkFormer: Masked Chunking Conformer for Long-Form Speech Transcription**
|
|
|
|
| 31 |
license: cc-by-nc-4.0
|
| 32 |
model-index:
|
| 33 |
- name: ChunkFormer Large Vietnamese
|
| 34 |
+
results:
|
| 35 |
+
- task:
|
| 36 |
+
name: Speech Recognition
|
| 37 |
+
type: automatic-speech-recognition
|
| 38 |
dataset:
|
| 39 |
+
name: common-voice-vietnamese
|
| 40 |
+
type: common_voice
|
| 41 |
+
args: vi
|
| 42 |
metrics:
|
| 43 |
+
- name: Test WER
|
| 44 |
+
type: wer
|
| 45 |
+
value: x
|
| 46 |
+
- task:
|
| 47 |
+
name: Speech Recognition
|
| 48 |
+
type: automatic-speech-recognition
|
| 49 |
dataset:
|
| 50 |
+
name: VIVOS
|
| 51 |
+
type: vivos
|
| 52 |
+
args: vi
|
| 53 |
metrics:
|
| 54 |
+
- name: Test WER
|
| 55 |
+
type: wer
|
| 56 |
+
value: x
|
| 57 |
+
- task:
|
| 58 |
+
name: Speech Recognition
|
| 59 |
+
type: automatic-speech-recognition
|
| 60 |
dataset:
|
| 61 |
+
name: VLSP - Task 1
|
| 62 |
+
type: vlsp
|
| 63 |
+
args: vi
|
| 64 |
metrics:
|
| 65 |
+
- name: Test WER
|
| 66 |
+
type: wer
|
| 67 |
+
value: x
|
| 68 |
---
|
| 69 |
|
| 70 |
# **ChunkFormer: Masked Chunking Conformer for Long-Form Speech Transcription**
|