Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Northern Sami
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use NbAiLab/whisper-large-sme with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/whisper-large-sme with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/whisper-large-sme")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLab/whisper-large-sme") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLab/whisper-large-sme", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update run.sh
Browse files
run.sh
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
torchrun --standalone --nnodes=1 --nproc_per_node=1 run_speech_recognition_seq2seq_streaming.py \
|
| 2 |
--model_name_or_path="openai/whisper-large-v2" \
|
| 3 |
-
--resume_from_checkpoint="checkpoint-60000" \
|
| 4 |
-
--ignore_data_skip \
|
| 5 |
--dataset_name="audiofolder" \
|
| 6 |
--dataset_data_dir="../data/dataset_wav" \
|
| 7 |
--language="finnish" \
|
|
@@ -36,7 +34,7 @@ torchrun --standalone --nnodes=1 --nproc_per_node=1 run_speech_recognition_seq2s
|
|
| 36 |
--predict_with_generate \
|
| 37 |
--do_normalize_eval \
|
| 38 |
--use_auth_token \
|
| 39 |
-
--overwrite_output_dir
|
| 40 |
--push_to_hub_organization="NbAiLab" \
|
| 41 |
--push_to_hub_model_id="whisper-large-sme" \
|
| 42 |
--push_to_hub
|
|
|
|
| 1 |
torchrun --standalone --nnodes=1 --nproc_per_node=1 run_speech_recognition_seq2seq_streaming.py \
|
| 2 |
--model_name_or_path="openai/whisper-large-v2" \
|
|
|
|
|
|
|
| 3 |
--dataset_name="audiofolder" \
|
| 4 |
--dataset_data_dir="../data/dataset_wav" \
|
| 5 |
--language="finnish" \
|
|
|
|
| 34 |
--predict_with_generate \
|
| 35 |
--do_normalize_eval \
|
| 36 |
--use_auth_token \
|
| 37 |
+
--overwrite_output_dir \
|
| 38 |
--push_to_hub_organization="NbAiLab" \
|
| 39 |
--push_to_hub_model_id="whisper-large-sme" \
|
| 40 |
--push_to_hub
|