Update README.md
Browse files
README.md
CHANGED
|
@@ -73,7 +73,7 @@ To transcribe audio in Catalan using this model, you can follow this example:
|
|
| 73 |
```python
|
| 74 |
from faster_whisper import WhisperModel
|
| 75 |
|
| 76 |
-
model_size = "
|
| 77 |
|
| 78 |
# Run on GPU with FP16
|
| 79 |
model = WhisperModel(model_size, device="cuda", compute_type="float16")
|
|
@@ -98,7 +98,7 @@ for segment in segments:
|
|
| 98 |
This model is not a direct result of training. It is a conversion of a [Whisper](https://huggingface.co/openai/whisper-large-v3) model using [faster-whisper](https://github.com/guillaumekln/faster-whisper/tree/master). The procedure to create the model is as follows:
|
| 99 |
|
| 100 |
```bash
|
| 101 |
-
ct2-transformers-converter --model
|
| 102 |
--output_dir faster-whisper-large-v3-ca-punctuated-3370h
|
| 103 |
--copy_files preprocessor_config.json
|
| 104 |
--quantization float16
|
|
@@ -106,25 +106,15 @@ ct2-transformers-converter --model https://huggingface.co/langtech-veu/whisper-l
|
|
| 106 |
|
| 107 |
## Citation
|
| 108 |
If this model contributes to your research, please cite the work:
|
| 109 |
-
```bibtex
|
| 110 |
-
@inproceedings{hernandez20243catparla,
|
| 111 |
-
title={3CatParla: A New Open-Source Corpus of Broadcast TV in Catalan for Automatic Speech Recognition},
|
| 112 |
-
author={Hern{\'a}ndez Mena, Carlos Daniel and Armentano Oller, Carme and Solito, Sarah and K{\"u}lebi, Baybars},
|
| 113 |
-
booktitle={Proc. IberSPEECH 2024},
|
| 114 |
-
pages={176--180},
|
| 115 |
-
year={2024}
|
| 116 |
-
}
|
| 117 |
```
|
| 118 |
-
|
| 119 |
-
<!--
|
| 120 |
@misc{mena2025whisperpunctuated,
|
| 121 |
title={Acoustic Model in Catalan: whisper-large-v3-ca-punctuated-3370h.},
|
| 122 |
-
author={Hernandez Mena, Carlos Daniel, Messaoudi Abir, Bonet, Cristina},
|
| 123 |
organization={Barcelona Supercomputing Center},
|
| 124 |
url={https://huggingface.co/langtech-veu/faster-whisper-large-v3-ca-punctuated-3370h},
|
| 125 |
year={2025}
|
| 126 |
}
|
| 127 |
-
|
| 128 |
|
| 129 |
## Additional Information
|
| 130 |
|
|
|
|
| 73 |
```python
|
| 74 |
from faster_whisper import WhisperModel
|
| 75 |
|
| 76 |
+
model_size = "langtech-veu/whisper-large-v3-ca-punctuated-3370h"
|
| 77 |
|
| 78 |
# Run on GPU with FP16
|
| 79 |
model = WhisperModel(model_size, device="cuda", compute_type="float16")
|
|
|
|
| 98 |
This model is not a direct result of training. It is a conversion of a [Whisper](https://huggingface.co/openai/whisper-large-v3) model using [faster-whisper](https://github.com/guillaumekln/faster-whisper/tree/master). The procedure to create the model is as follows:
|
| 99 |
|
| 100 |
```bash
|
| 101 |
+
ct2-transformers-converter --model langtech-veu/whisper-large-v3-ca-punctuated-3370h
|
| 102 |
--output_dir faster-whisper-large-v3-ca-punctuated-3370h
|
| 103 |
--copy_files preprocessor_config.json
|
| 104 |
--quantization float16
|
|
|
|
| 106 |
|
| 107 |
## Citation
|
| 108 |
If this model contributes to your research, please cite the work:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
```
|
|
|
|
|
|
|
| 110 |
@misc{mena2025whisperpunctuated,
|
| 111 |
title={Acoustic Model in Catalan: whisper-large-v3-ca-punctuated-3370h.},
|
| 112 |
+
author={Hernandez Mena, Carlos Daniel, Messaoudi, Abir, España-Bonet, Cristina},
|
| 113 |
organization={Barcelona Supercomputing Center},
|
| 114 |
url={https://huggingface.co/langtech-veu/faster-whisper-large-v3-ca-punctuated-3370h},
|
| 115 |
year={2025}
|
| 116 |
}
|
| 117 |
+
```
|
| 118 |
|
| 119 |
## Additional Information
|
| 120 |
|