Commit
·
b8f225a
1
Parent(s):
24792f9
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,12 +19,7 @@ model-index:
|
|
| 19 |
# Model Card for Model ID
|
| 20 |
|
| 21 |
This is a finetune for Whisper Small. A finetune to achieve better results on Whisper Small for Portuguese.
|
| 22 |
-
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation.
|
| 23 |
-
of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need
|
| 24 |
-
for fine-tuning.
|
| 25 |
-
|
| 26 |
-
Whisper was proposed in the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)
|
| 27 |
-
by Alec Radford et al from OpenAI. The original code repository can be found [here](https://github.com/openai/whisper).
|
| 28 |
|
| 29 |
|
| 30 |
## Model Details
|
|
@@ -32,15 +27,7 @@ by Alec Radford et al from OpenAI. The original code repository can be found [he
|
|
| 32 |
Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model.
|
| 33 |
It was trained on 680k hours of labelled speech data annotated using large-scale weak supervision.
|
| 34 |
|
| 35 |
-
|
| 36 |
-
on the task of speech recognition. The multilingual models were trained on both speech recognition and speech
|
| 37 |
-
translation. For speech recognition, the model predicts transcriptions in the *same* language as the audio.
|
| 38 |
-
For speech translation, the model predicts transcriptions to a *different* language to the audio.
|
| 39 |
-
|
| 40 |
-
Whisper checkpoints come in five configurations of varying model sizes.
|
| 41 |
-
The smallest four are trained on either English-only or multilingual data.
|
| 42 |
-
The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints
|
| 43 |
-
are available on the [Hugging Face Hub](https://huggingface.co/models?search=openai/whisper).
|
| 44 |
|
| 45 |
- **Developed by:** [ArtificialGuyBr](https://twitter.com/@artificialguybr)
|
| 46 |
- **Shared by:** [ArtificialGuyBr](https://twitter.com/@artificialguybr)
|
|
|
|
| 19 |
# Model Card for Model ID
|
| 20 |
|
| 21 |
This is a finetune for Whisper Small. A finetune to achieve better results on Whisper Small for Portuguese.
|
| 22 |
+
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
|
| 25 |
## Model Details
|
|
|
|
| 27 |
Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model.
|
| 28 |
It was trained on 680k hours of labelled speech data annotated using large-scale weak supervision.
|
| 29 |
|
| 30 |
+
This is a finetune using Common Voice 13.0 to improve the results for PORTUGUESE.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
- **Developed by:** [ArtificialGuyBr](https://twitter.com/@artificialguybr)
|
| 33 |
- **Shared by:** [ArtificialGuyBr](https://twitter.com/@artificialguybr)
|