Hugging Face's logo

nvidia
/
canary-1b

Automatic Speech Recognition
NeMo
PyTorch
4 languages
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results
Model card Files Community
25

Update README.md

#24
by steveheh - opened
base: refs/heads/main
←
from: refs/pr/24
Discussion Files changed
+6
-6
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -137,7 +137,7 @@ model-index:
137
  metrics:
138
  - name: Test BLEU (En->De)
139
  type: bleu
140
- value: 22.66
141
  - task:
142
  type: Automatic Speech Translation
143
  name: automatic-speech-translation
@@ -151,7 +151,7 @@ model-index:
151
  metrics:
152
  - name: Test BLEU (En->Es)
153
  type: bleu
154
- value: 41.11
155
  - task:
156
  type: Automatic Speech Translation
157
  name: automatic-speech-translation
@@ -179,7 +179,7 @@ model-index:
179
  metrics:
180
  - name: Test BLEU (De->En)
181
  type: bleu
182
- value: 32.64
183
  - task:
184
  type: Automatic Speech Translation
185
  name: automatic-speech-translation
@@ -193,7 +193,7 @@ model-index:
193
  metrics:
194
  - name: Test BLEU (Es->En)
195
  type: bleu
196
- value: 32.15
197
  - task:
198
  type: Automatic Speech Translation
199
  name: automatic-speech-translation
@@ -207,7 +207,7 @@ model-index:
207
  metrics:
208
  - name: Test BLEU (Fr->En)
209
  type: bleu
210
- value: 23.57
211
  - task:
212
  type: Automatic Speech Translation
213
  name: automatic-speech-translation
@@ -481,7 +481,7 @@ BLEU score on [FLEURS](https://huggingface.co/datasets/google/fleurs) test set:
481
 
482
  | **Version** | **Model** | **En->De** | **En->Es** | **En->Fr** | **De->En** | **Es->En** | **Fr->En** |
483
  |:-----------:|:---------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
484
- | 1.23.0 | canary-1b | 32.13 | 22.66 | 40.76 | 33.98 | 21.80 | 30.95 |
485
 
486
 
487
  BLEU score on [COVOST-v2](https://github.com/facebookresearch/covost) test set:
 
137
  metrics:
138
  - name: Test BLEU (En->De)
139
  type: bleu
140
+ value: 32.15
141
  - task:
142
  type: Automatic Speech Translation
143
  name: automatic-speech-translation
 
151
  metrics:
152
  - name: Test BLEU (En->Es)
153
  type: bleu
154
+ value: 22.66
155
  - task:
156
  type: Automatic Speech Translation
157
  name: automatic-speech-translation
 
179
  metrics:
180
  - name: Test BLEU (De->En)
181
  type: bleu
182
+ value: 33.98
183
  - task:
184
  type: Automatic Speech Translation
185
  name: automatic-speech-translation
 
193
  metrics:
194
  - name: Test BLEU (Es->En)
195
  type: bleu
196
+ value: 21.80
197
  - task:
198
  type: Automatic Speech Translation
199
  name: automatic-speech-translation
 
207
  metrics:
208
  - name: Test BLEU (Fr->En)
209
  type: bleu
210
+ value: 30.95
211
  - task:
212
  type: Automatic Speech Translation
213
  name: automatic-speech-translation
 
481
 
482
  | **Version** | **Model** | **En->De** | **En->Es** | **En->Fr** | **De->En** | **Es->En** | **Fr->En** |
483
  |:-----------:|:---------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
484
+ | 1.23.0 | canary-1b | 32.15 | 22.66 | 40.76 | 33.98 | 21.80 | 30.95 |
485
 
486
 
487
  BLEU score on [COVOST-v2](https://github.com/facebookresearch/covost) test set: