Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ The fine-tuned model achieves the following performance :
|
|
| 28 |
|:-------------:|:--------------:|:--------------:| :--------:|:--------:|
|
| 29 |
| 2023-09-08 | 9.14 | 11.21 | 4xV100 32GB | 30 |
|
| 30 |
|
| 31 |
-
## Model Details
|
| 32 |
|
| 33 |
The ASR system is composed of:
|
| 34 |
- the **Tokenizer** (char) that transforms the input text into a sequence of characters ("cat" into ["c", "a", "t"]) and trained with the train transcriptions (train.tsv).
|
|
@@ -37,7 +37,7 @@ The final acoustic representation is given to the CTC greedy decode.
|
|
| 37 |
|
| 38 |
We used recordings sampled at 16kHz (single channel).
|
| 39 |
|
| 40 |
-
## How to transcribe a file with the model
|
| 41 |
|
| 42 |
### Install and import speechbrain
|
| 43 |
|
|
@@ -67,7 +67,7 @@ def main():
|
|
| 67 |
save_transcript(transcript, audio, "out.txt")
|
| 68 |
```
|
| 69 |
|
| 70 |
-
## Training Details
|
| 71 |
|
| 72 |
### Training Data
|
| 73 |
|
|
@@ -104,7 +104,7 @@ With 4xV100 32GB, the training took ~ 81 hours.
|
|
| 104 |
}
|
| 105 |
```
|
| 106 |
|
| 107 |
-
## Information
|
| 108 |
|
| 109 |
- **Developed by:** Cécile Macaire
|
| 110 |
- **Funded by [optional]:** GENCI-IDRIS (Grant 2023-AD011013625R1)
|
|
@@ -113,7 +113,7 @@ PROPICTO ANR-20-CE93-0005
|
|
| 113 |
- **License:** Apache-2.0
|
| 114 |
- **Finetuned from model:** LeBenchmark/wav2vec2-FR-7K-large
|
| 115 |
|
| 116 |
-
## Citation
|
| 117 |
|
| 118 |
```bibtex
|
| 119 |
@inproceedings{macaire24_interspeech,
|
|
|
|
| 28 |
|:-------------:|:--------------:|:--------------:| :--------:|:--------:|
|
| 29 |
| 2023-09-08 | 9.14 | 11.21 | 4xV100 32GB | 30 |
|
| 30 |
|
| 31 |
+
## 📝 Model Details
|
| 32 |
|
| 33 |
The ASR system is composed of:
|
| 34 |
- the **Tokenizer** (char) that transforms the input text into a sequence of characters ("cat" into ["c", "a", "t"]) and trained with the train transcriptions (train.tsv).
|
|
|
|
| 37 |
|
| 38 |
We used recordings sampled at 16kHz (single channel).
|
| 39 |
|
| 40 |
+
## 💻 How to transcribe a file with the model
|
| 41 |
|
| 42 |
### Install and import speechbrain
|
| 43 |
|
|
|
|
| 67 |
save_transcript(transcript, audio, "out.txt")
|
| 68 |
```
|
| 69 |
|
| 70 |
+
## ⚙️ Training Details
|
| 71 |
|
| 72 |
### Training Data
|
| 73 |
|
|
|
|
| 104 |
}
|
| 105 |
```
|
| 106 |
|
| 107 |
+
## 💡 Information
|
| 108 |
|
| 109 |
- **Developed by:** Cécile Macaire
|
| 110 |
- **Funded by [optional]:** GENCI-IDRIS (Grant 2023-AD011013625R1)
|
|
|
|
| 113 |
- **License:** Apache-2.0
|
| 114 |
- **Finetuned from model:** LeBenchmark/wav2vec2-FR-7K-large
|
| 115 |
|
| 116 |
+
## 📌 Citation
|
| 117 |
|
| 118 |
```bibtex
|
| 119 |
@inproceedings{macaire24_interspeech,
|