Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use NbAiLab/whisper-tiny-nob with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/whisper-tiny-nob with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/whisper-tiny-nob")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLab/whisper-tiny-nob") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLab/whisper-tiny-nob", device_map="auto") - Notebooks
- Google Colab
- Kaggle
first
Browse files
run.sh
CHANGED
|
@@ -13,9 +13,9 @@ python run_speech_recognition_seq2seq_streaming.py \
|
|
| 13 |
--logging_steps="50" \
|
| 14 |
--learning_rate="1e-5" \
|
| 15 |
--lr_scheduler_type="constant_with_warmup" \
|
| 16 |
-
--warmup_steps="
|
| 17 |
--evaluation_strategy="steps" \
|
| 18 |
-
--eval_steps="
|
| 19 |
--save_strategy="steps" \
|
| 20 |
--save_steps="500" \
|
| 21 |
--generation_max_length="225" \
|
|
|
|
| 13 |
--logging_steps="50" \
|
| 14 |
--learning_rate="1e-5" \
|
| 15 |
--lr_scheduler_type="constant_with_warmup" \
|
| 16 |
+
--warmup_steps="1000" \
|
| 17 |
--evaluation_strategy="steps" \
|
| 18 |
+
--eval_steps="500" \
|
| 19 |
--save_strategy="steps" \
|
| 20 |
--save_steps="500" \
|
| 21 |
--generation_max_length="225" \
|