Instructions to use lsnoo/russian_fairseq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lsnoo/russian_fairseq with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lsnoo/russian_fairseq")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("lsnoo/russian_fairseq") model = AutoModelForCTC.from_pretrained("lsnoo/russian_fairseq", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,17 +1,18 @@
|
|
| 1 |
Wav2vec2.0-xlsr-53 model is fine-tuned on commonvoice russian dataset
|
| 2 |
|
| 3 |
Configs (yaml)
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
| 7 |
keep_interval_updates: 1
|
| 8 |
no_epoch_ckechpoints: true
|
| 9 |
best_checkpoint_metric: wer
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
---num_workers: 6
|
| 16 |
---max_tokens: 800000
|
| 17 |
---skip_invalid_size_inputs_valid_test: true
|
|
|
|
| 1 |
Wav2vec2.0-xlsr-53 model is fine-tuned on commonvoice russian dataset
|
| 2 |
|
| 3 |
Configs (yaml)
|
| 4 |
+
|
| 5 |
+
checkpoint:
|
| 6 |
+
save_interval: 1000 \n
|
| 7 |
+
save_interval_updates: 1000 \n
|
| 8 |
keep_interval_updates: 1
|
| 9 |
no_epoch_ckechpoints: true
|
| 10 |
best_checkpoint_metric: wer
|
| 11 |
+
task:
|
| 12 |
+
_name: audio_finetuning
|
| 13 |
+
normalize: true
|
| 14 |
+
labels: phn
|
| 15 |
+
dataset:
|
| 16 |
---num_workers: 6
|
| 17 |
---max_tokens: 800000
|
| 18 |
---skip_invalid_size_inputs_valid_test: true
|