Automatic Speech Recognition
Transformers
Safetensors
Portuguese
wav2vec2-bert
Generated from Trainer
asr
w2v-bert-2.0
Eval Results (legacy)
Instructions to use tiagomosantos/w2v-bert-2.0-pt_pt_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiagomosantos/w2v-bert-2.0-pt_pt_v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="tiagomosantos/w2v-bert-2.0-pt_pt_v2")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("tiagomosantos/w2v-bert-2.0-pt_pt_v2") model = AutoModelForCTC.from_pretrained("tiagomosantos/w2v-bert-2.0-pt_pt_v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,9 +38,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 38 |
|
| 39 |
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_16_1 Portuguese subset using 1XRTX 3090.
|
| 40 |
It achieves the following results on the test set:
|
| 41 |
-
- Wer: 0.
|
| 42 |
-
- Cer: 0.
|
| 43 |
-
- Bert Score: 0.
|
|
|
|
| 44 |
|
| 45 |
## Model description
|
| 46 |
|
|
|
|
| 38 |
|
| 39 |
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_16_1 Portuguese subset using 1XRTX 3090.
|
| 40 |
It achieves the following results on the test set:
|
| 41 |
+
- Wer: 0.10491320595991134
|
| 42 |
+
- Cer: 0.032070871626631914
|
| 43 |
+
- Bert Score: 0.9619712047981167
|
| 44 |
+
- Sentence Similarity: 0.93867844
|
| 45 |
|
| 46 |
## Model description
|
| 47 |
|