Updated paths to match move to CoRal-project

README.md

@@ -45,7 +45,7 @@ model-index:
 pipeline_tag: automatic-speech-recognition
 ---
 
-# Røst-315m
+# Røst-Wav2Vec2-315m-v1
 
 This is a Danish state-of-the-art speech recognition model, trained by [the Alexandra
 Institute](https://alexandra.dk/).
@@ -65,7 +65,7 @@ Next you can use the model using the `transformers` Python package as follows:
 ```python
 >>> from transformers import pipeline
 >>> audio = get_audio()  # 16kHz raw audio array
->>> transcriber = pipeline(model="alexandrainst/roest-315m")
+>>> transcriber = pipeline(model="CoRal-project/roest-wav2vec2-315m-v1")
 >>> transcriber(audio)
 {'text': 'your transcription'}
 ```
@@ -79,9 +79,9 @@ bootstrapped the results 1000 times and report here the mean scores along with a
 confidence interval (lower is better; best scores in **bold**, second-best in
 *italics*):
 
-| Model | Number of parameters | [CoRal](https://huggingface.co/datasets/alexandrainst/coral/viewer/read_aloud/test) CER | [CoRal](https://huggingface.co/datasets/alexandrainst/coral/viewer/read_aloud/test) WER | [Danish Common Voice 17](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/viewer/da/test) CER | [Danish Common Voice 17](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/viewer/da/test) WER |
+| Model | Number of parameters | [CoRal](https://huggingface.co/datasets/CoRal-project/coral/viewer/read_aloud/test) CER | [CoRal](https://huggingface.co/datasets/CoRal-project/coral/viewer/read_aloud/test) WER | [Danish Common Voice 17](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/viewer/da/test) CER | [Danish Common Voice 17](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/viewer/da/test) WER |
 |:---|---:|---:|---:|---:|---:|
-| Røst-315m (this model) | 315M | **6.6% ± 0.2%** | **17.0% ± 0.4%** | 6.6% ± 0.6% | 16.7% ± 0.8% |
+|CoRal-project/roest-wav2vec2-315m-v1 (this model) | 315M | **6.6% ± 0.2%** | **17.0% ± 0.4%** | 6.6% ± 0.6% | 16.7% ± 0.8% |
 | [chcaa/xls-r-300m-danish-nst-cv9](https://hf.co/chcaa/xls-r-300m-danish-nst-cv9) | 315M | 14.4% ± 0.3% | 36.5% ± 0.6% | **4.1% ± 0.5%** | **12.0% ± 0.8%** |
 | [mhenrichsen/hviske](https://hf.co/mhenrichsen/hviske) | 1540M | 14.2% ± 0.5% | 33.2% ± 0.7% | *5.2% ± 0.4%* | *14.2% ± 0.8%* |
 | [openai/whisper-large-v3](https://hf.co/openai/whisper-large-v3) | 1540M | *11.4% ± 0.3%* | *28.3% ± 0.6%* | *5.5% ± 0.4%* | *14.8% ± 0.8%* |
@@ -127,7 +127,7 @@ This model is the result of four different stages of training:
      both audio and transcriptions to perform the speech-to-text task (also known as
      automatic speech recognition). The finetuning data is as follows:
      - The read-aloud training split of the [CoRal
-       dataset](https://huggingface.co/datasets/alexandrainst/coral) (revision
+       dataset](https://huggingface.co/datasets/CoRal-project/coral) (revision
        fb20199b3966d3373e0d3a5ded2c5920c70de99c), consisting of 361 hours of Danish
        read-aloud speech, diverse across dialects, accents, ages and genders.
   3. An n-gram language model has been trained separately, and is used to guide the
@@ -147,7 +147,7 @@ This model is the result of four different stages of training:
 
 The first step was trained by [Babu et al.
 (2021)](https://doi.org/10.48550/arXiv.2111.09296) and the second and third step by
-[Nielsen et al. (2024)](https://huggingface.co/alexandrainst/roest-315m).
+[Nielsen et al. (2024)](https://huggingface.co/CoRal-project/roest-wav2vec2-315m-v1).
 
 The final product is then the combination of the finetuned model along with the n-gram
 model, and this is what is used when you use the model as mentioned in the Quick Start
@@ -160,7 +160,7 @@ This model is intended to be used for Danish automatic speech recognition.
 
 Note that Biometric Identification is not allowed using the CoRal dataset and/or derived
 models. For more information, see addition 4 in our
-[license](https://huggingface.co/alexandrainst/roest-315m/blob/main/LICENSE).
+[license](https://huggingface.co/CoRal-project/roest-wav2vec2-315m-v1/blob/main/LICENSE).
 
 
 ## Why the name Røst?
@@ -175,7 +175,7 @@ Scandinavia](https://da.wikipedia.org/wiki/Koralrev#Koldtvandskoralrev).
 The dataset is licensed under a custom license, adapted from OpenRAIL-M, which allows
 commercial use with a few restrictions (speech synthesis and biometric identification).
 See
-[license](https://huggingface.co/alexandrainst/roest-315m/blob/main/LICENSE).
+[license](https://huggingface.co/CoRal-project/roest-wav2vec2-315m-v1/blob/main/LICENSE).
 
 
 ## Creators and Funders