Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
Safetensors
English
speech_to_text
audio
Instructions to use facebook/s2t-medium-librispeech-asr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/s2t-medium-librispeech-asr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/s2t-medium-librispeech-asr")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("facebook/s2t-medium-librispeech-asr") model = AutoModelForSpeechSeq2Seq.from_pretrained("facebook/s2t-medium-librispeech-asr") - Notebooks
- Google Colab
- Kaggle
Update README.md
#2
by kbthebest181 - opened
README.md
CHANGED
|
@@ -53,7 +53,7 @@ from datasets import load_dataset
|
|
| 53 |
import soundfile as sf
|
| 54 |
|
| 55 |
model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-medium-librispeech-asr")
|
| 56 |
-
processor =
|
| 57 |
|
| 58 |
def map_to_array(batch):
|
| 59 |
speech, _ = sf.read(batch["file"])
|
|
|
|
| 53 |
import soundfile as sf
|
| 54 |
|
| 55 |
model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-medium-librispeech-asr")
|
| 56 |
+
processor = Speech2TextProcessor.from_pretrained("facebook/s2t-medium-librispeech-asr")
|
| 57 |
|
| 58 |
def map_to_array(batch):
|
| 59 |
speech, _ = sf.read(batch["file"])
|