Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Yue Chinese
whisper
whisper-event
hf-asr-leaderboard
Generated from Trainer
Eval Results (legacy)
Instructions to use simonl0909/whisper-large-v2-cantonese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use simonl0909/whisper-large-v2-cantonese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="simonl0909/whisper-large-v2-cantonese")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("simonl0909/whisper-large-v2-cantonese") model = AutoModelForSpeechSeq2Seq.from_pretrained("simonl0909/whisper-large-v2-cantonese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
c3f0671
1
Parent(s): 7c766c3
Librarian Bot: Add base_model information to model (#3)
Browse files- Librarian Bot: Add base_model information to model (eb73590e8ab83b3a2ce2c5f7d71569572b3600c1)
Co-authored-by: Librarian Bot (Bot) <librarian-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -10,32 +10,33 @@ datasets:
|
|
| 10 |
- mozilla-foundation/common_voice_11_0
|
| 11 |
metrics:
|
| 12 |
- cer
|
|
|
|
| 13 |
model-index:
|
| 14 |
- name: Whisper Large V2 Cantonese
|
| 15 |
results:
|
| 16 |
- task:
|
| 17 |
-
name: Automatic Speech Recognition
|
| 18 |
type: automatic-speech-recognition
|
|
|
|
| 19 |
dataset:
|
| 20 |
name: mozilla-foundation/common_voice_11_0
|
| 21 |
type: mozilla-foundation/common_voice_11_0
|
| 22 |
-
split: test
|
| 23 |
config: yue
|
|
|
|
| 24 |
metrics:
|
| 25 |
-
-
|
| 26 |
-
type: cer
|
| 27 |
value: 6.7274
|
|
|
|
| 28 |
- task:
|
| 29 |
-
name: Speech Recognition
|
| 30 |
type: automatic-speech-recognition
|
|
|
|
| 31 |
dataset:
|
| 32 |
name: Common Voice zh-HK
|
| 33 |
type: common_voice
|
| 34 |
args: zh-HK
|
| 35 |
metrics:
|
| 36 |
-
-
|
| 37 |
-
type: cer
|
| 38 |
value: 6.7274
|
|
|
|
| 39 |
---
|
| 40 |
|
| 41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 10 |
- mozilla-foundation/common_voice_11_0
|
| 11 |
metrics:
|
| 12 |
- cer
|
| 13 |
+
base_model: openai/whisper-large-v2
|
| 14 |
model-index:
|
| 15 |
- name: Whisper Large V2 Cantonese
|
| 16 |
results:
|
| 17 |
- task:
|
|
|
|
| 18 |
type: automatic-speech-recognition
|
| 19 |
+
name: Automatic Speech Recognition
|
| 20 |
dataset:
|
| 21 |
name: mozilla-foundation/common_voice_11_0
|
| 22 |
type: mozilla-foundation/common_voice_11_0
|
|
|
|
| 23 |
config: yue
|
| 24 |
+
split: test
|
| 25 |
metrics:
|
| 26 |
+
- type: cer
|
|
|
|
| 27 |
value: 6.7274
|
| 28 |
+
name: Cer
|
| 29 |
- task:
|
|
|
|
| 30 |
type: automatic-speech-recognition
|
| 31 |
+
name: Speech Recognition
|
| 32 |
dataset:
|
| 33 |
name: Common Voice zh-HK
|
| 34 |
type: common_voice
|
| 35 |
args: zh-HK
|
| 36 |
metrics:
|
| 37 |
+
- type: cer
|
|
|
|
| 38 |
value: 6.7274
|
| 39 |
+
name: Test CER
|
| 40 |
---
|
| 41 |
|
| 42 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|