Instructions to use espnet/DCASE23.AudioCaptioning.FineTuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/DCASE23.AudioCaptioning.FineTuned with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/DCASE23.AudioCaptioning.FineTuned" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Set pipeline_tag: automatic-speech-recognition
Browse files
README.md
CHANGED
|
@@ -9,4 +9,5 @@ datasets:
|
|
| 9 |
- slseanwu/clotho-chatgpt-mixup-50K
|
| 10 |
- audiocaps
|
| 11 |
license: cc-by-4.0
|
| 12 |
-
--
|
|
|
|
|
|
| 9 |
- slseanwu/clotho-chatgpt-mixup-50K
|
| 10 |
- audiocaps
|
| 11 |
license: cc-by-4.0
|
| 12 |
+
pipeline_tag: automatic-speech-recognition
|
| 13 |
+
---
|