Automatic Speech Recognition
ESPnet
multilingual
audio
phone-recognition
grapheme-to-phoneme
phoneme-to-grapheme
Instructions to use espnet/powsm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/powsm with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/powsm" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Create meta.yaml
Browse files
textnorm_retrained/meta.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
espnet: '202511' # with unmerged local change; will update to suitable version
|
| 2 |
+
files:
|
| 3 |
+
s2t_model_file: exp/s2t_train_ctc3_conv2d_size768_e9_d9_mel128_raw_bpe40000/valid.acc.ave_5best.till45epoch.pth
|
| 4 |
+
python: 3.12.8
|
| 5 |
+
torch: 2.9.1+cu128
|
| 6 |
+
yaml_files:
|
| 7 |
+
s2t_train_config: exp/s2t_train_ctc3_conv2d_size768_e9_d9_mel128_raw_bpe40000/config.yaml
|