Automatic Speech Recognition
Transformers
Safetensors
Lingala
vits
text-to-audio
audio
speech
african-languages
multilingual
simba
low-resource
speech-recognition
asr
Instructions to use UBC-NLP/Simba-TTS-lin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UBC-NLP/Simba-TTS-lin with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="UBC-NLP/Simba-TTS-lin")# Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("UBC-NLP/Simba-TTS-lin") model = AutoModelForTextToWaveform.from_pretrained("UBC-NLP/Simba-TTS-lin") - Notebooks
- Google Colab
- Kaggle
Upload feature extractor
Browse files- preprocessor_config.json +11 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor_type": "VitsFeatureExtractor",
|
| 3 |
+
"feature_size": 80,
|
| 4 |
+
"hop_length": 256,
|
| 5 |
+
"max_wav_value": 32768.0,
|
| 6 |
+
"n_fft": 1024,
|
| 7 |
+
"padding_side": "right",
|
| 8 |
+
"padding_value": 0.0,
|
| 9 |
+
"return_attention_mask": false,
|
| 10 |
+
"sampling_rate": 16000
|
| 11 |
+
}
|