Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Urdu
wav2vec2
hf-asr-leaderboard
robust-speech-event
Eval Results (legacy)
Instructions to use kingabzpro/wav2vec2-60-urdu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kingabzpro/wav2vec2-60-urdu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="kingabzpro/wav2vec2-60-urdu")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("kingabzpro/wav2vec2-60-urdu") model = AutoModelForCTC.from_pretrained("kingabzpro/wav2vec2-60-urdu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
ed37d85
1
Parent(s): a0d7b6c
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,13 +12,13 @@ metrics:
|
|
| 12 |
- wer
|
| 13 |
- cer
|
| 14 |
model-index:
|
| 15 |
-
- name: wav2vec2-
|
| 16 |
results:
|
| 17 |
- task:
|
| 18 |
type: automatic-speech-recognition # Required. Example: automatic-speech-recognition
|
| 19 |
name: Urdu Speech Recognition # Optional. Example: Speech Recognition
|
| 20 |
dataset:
|
| 21 |
-
type:
|
| 22 |
name: Urdu # Required. Example: Common Voice zh-CN
|
| 23 |
args: ur # Optional. Example: zh-CN
|
| 24 |
metrics:
|
|
|
|
| 12 |
- wer
|
| 13 |
- cer
|
| 14 |
model-index:
|
| 15 |
+
- name: wav2vec2-60-urdu
|
| 16 |
results:
|
| 17 |
- task:
|
| 18 |
type: automatic-speech-recognition # Required. Example: automatic-speech-recognition
|
| 19 |
name: Urdu Speech Recognition # Optional. Example: Speech Recognition
|
| 20 |
dataset:
|
| 21 |
+
type: common_voice_7 # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
|
| 22 |
name: Urdu # Required. Example: Common Voice zh-CN
|
| 23 |
args: ur # Optional. Example: zh-CN
|
| 24 |
metrics:
|