Automatic Speech Recognition
Transformers
Safetensors
English
Italian
conformer_encoder_decoder
speech
speech recognition
speech translation
ASR
ST
custom_code
Instructions to use FBK-MT/fama-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FBK-MT/fama-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="FBK-MT/fama-medium", trust_remote_code=True)# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("FBK-MT/fama-medium", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add arXiv link
Browse files
README.md
CHANGED
|
@@ -51,7 +51,7 @@ It is available in 2 sizes, with 2 variants for ASR only:
|
|
| 51 |
- [FAMA-small-asr](https://huggingface.co/FBK-MT/fama-small-asr) - 475 million parameters
|
| 52 |
- [FAMA-medium-asr](https://huggingface.co/FBK-MT/fama-medium-asr) - 878 million parameters
|
| 53 |
|
| 54 |
-
For more information about FAMA, please check our [blog post](https://huggingface.co/blog/FAMA/release) and the [arXiv](https://arxiv.org/) preprint.
|
| 55 |
|
| 56 |
## Usage
|
| 57 |
|
|
|
|
| 51 |
- [FAMA-small-asr](https://huggingface.co/FBK-MT/fama-small-asr) - 475 million parameters
|
| 52 |
- [FAMA-medium-asr](https://huggingface.co/FBK-MT/fama-medium-asr) - 878 million parameters
|
| 53 |
|
| 54 |
+
For more information about FAMA, please check our [blog post](https://huggingface.co/blog/FAMA/release) and the [arXiv](https://arxiv.org/abs/2505.22759) preprint.
|
| 55 |
|
| 56 |
## Usage
|
| 57 |
|