Automatic Speech Recognition
NeMo
PyTorch
Swahili
speech
Swahili
audio
CTC
Conformer
Transformer
NeMo
Instructions to use de-coder/stt_sw_ctc_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use de-coder/stt_sw_ctc_model with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("de-coder/stt_sw_ctc_model") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -48,11 +48,11 @@ asr_model = nemo_asr.models.ASRModel.from_pretrained("decoder/STT_SW_Model")
|
|
| 48 |
### Transcribing using Python
|
| 49 |
First, let's get a sample
|
| 50 |
```
|
| 51 |
-
wget https://
|
| 52 |
```
|
| 53 |
-
Then simply do:
|
| 54 |
```
|
| 55 |
-
asr_model.transcribe([
|
| 56 |
```
|
| 57 |
|
| 58 |
### Transcribing many audio files
|
|
|
|
| 48 |
### Transcribing using Python
|
| 49 |
First, let's get a sample
|
| 50 |
```
|
| 51 |
+
!wget https://filebin.net/198phynus62ua08w/common_voice_sw_27777611.wav
|
| 52 |
```
|
| 53 |
+
Then simply do: if in colab
|
| 54 |
```
|
| 55 |
+
transcriptions = asr_model.transcribe(["/content/common_voice_sw_27777611.wav"])
|
| 56 |
```
|
| 57 |
|
| 58 |
### Transcribing many audio files
|