Update README.md

README.md

@@ -16,14 +16,14 @@ metrics:
 - cer
 - cher
 model-index:
-- name: slu-wav2vec2-ctc-MEDIA-relax
+- name: slu-wav2vec2-ctc-MEDIA-full
   results:
   - task:
       name: Spoken Language Understanding
       type: spoken-language-understanding
     dataset:
       name: MEDIA
-      type: MEDIA_slu_relax
+      type: MEDIA_slu_full
       config: fr
       split: test
       args:
@@ -31,13 +31,13 @@ model-index:
     metrics:
     - name: Test ChER
       type: cher
-      value: 7.46
+      value: 7.78
     - name: Test CER
       type: cer
-      value: 20.10
+      value: 24.88
     - name: Test CVER
       type: cver
-      value: 31.41
+      value: 35.77
 ---
 
 <iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
@@ -54,7 +54,7 @@ The performance of the model is the following:
 
 | Release | Test ChER | Test CER | Test CVER | GPUs |
 |:-------------:|:--------------:|:--------------:|:--------------:|:--------:|
-| 22-02-23 | 7.46 | 20.10 | 31.41 | 1xV100 32GB |
+| 22-02-23 | 7.78 | 24.88 | 35.77 | 1xV100 32GB |
 
 ## Pipeline description
 
@@ -80,7 +80,7 @@ Please notice that we encourage you to read our tutorials and learn more about
 ```python
 from speechbrain.pretrained import EncoderASR
 
-asr_model = EncoderASR.from_hparams(source="speechbrain/slu-wav2vec2-ctc-MEDIA-relax", savedir="pretrained_models/slu-wav2vec2-ctc-MEDIA-relax")
+asr_model = EncoderASR.from_hparams(source="speechbrain/slu-wav2vec2-ctc-MEDIA-full", savedir="pretrained_models/slu-wav2vec2-ctc-MEDIA-full")
 asr_model.transcribe_file('speechbrain/asr-wav2vec2-commonvoice-fr/example-fr.wav')
 
 ```
@@ -104,7 +104,7 @@ pip install -e .
 - [Media ASR (ELRA-S0272)](https://catalogue.elra.info/en-us/repository/browse/ELRA-S0272/)
 - [Media SLU (ELRA-E0024)](https://catalogue.elra.info/en-us/repository/browse/ELRA-E0024/)
 - [channels.csv and concepts_full_relax.csv](https://drive.google.com/drive/u/1/folders/1z2zFZp3c0NYLFaUhhghhBakGcFdXVRyf)
-4. Modify placeholders in hparams/train_hf_wav2vec_relax.yaml:
+4. Modify placeholders in hparams/train_hf_wav2vec_full.yaml:
 ```bash
 data_folder = !PLACEHOLDER
 channels_path = !PLACEHOLDER
@@ -113,10 +113,10 @@ concepts_path = !PLACEHOLDER
 5. Run Training:
 ```bash
 cd recipes/MEDIA/SLU/CTC/
-python train_hf_wav2vec.py hparams/train_hf_wav2vec_relax.yaml
+python train_hf_wav2vec.py hparams/train_hf_wav2vec_full.yaml
 ```
 
-You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1ALtwmk3VUUM0XRToecQp1DKAh9FsGqMA?usp=sharing).
+You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1cZRRQ3Cc_ucXXlwYSJqB7pOl6KwZdo84?usp=share_link).
 
 ### Limitations
 The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.