Adding info to the README file.

README.md

@@ -1,3 +1,200 @@
 ---
+language: is
+datasets:
+- language-and-voice-lab/samromur_asr
+- language-and-voice-lab/samromur_children
+- language-and-voice-lab/malromur_asr
+- language-and-voice-lab/althingi_asr
+tags:
+- audio
+- automatic-speech-recognition
+- icelandic
+- whisper
+- whisper-large
+- iceland
+- reykjavik
+- samromur
 license: cc-by-4.0
+widget:
+model-index:
+- name: whisper-large-icelandic-10k-steps-1000h
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Samrómur (Test)
+      type: language-and-voice-lab/samromur_asr
+      split: test
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 11.879
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Samrómur (Dev)
+      type: language-and-voice-lab/samromur_asr
+      split: validation
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 10.849
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Samrómur Children (Test)
+      type: language-and-voice-lab/samromur_children
+      split: test
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 12.325
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Samrómur Children (Dev)
+      type: language-and-voice-lab/samromur_children
+      split: validation
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 8.078
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Malrómur (Test)
+      type: language-and-voice-lab/malromur_asr
+      split: test
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 10.132
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Malrómur (Dev)
+      type: language-and-voice-lab/malromur_asr
+      split: validation
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 10.157
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Althingi (Test)
+      type: language-and-voice-lab/althingi_asr
+      split: test
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 11.750
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Althingi (Dev)
+      type: language-and-voice-lab/althingi_asr
+      split: validation
+      args: 
+        language: is
+    metrics:
+    - name: WER
+      type: wer
+      value: 11.141
 ---
+# whisper-large-icelandic-10k-steps-1000h
+
+The "whisper-large-icelandic-10k-steps-1000h" is an acoustic model suitable for Automatic Speech Recognition in Icelandic. It is the result of fine-tuning the model "openai/whisper-large" with around 1000 hours of Icelandic data developed by the [Language and Voice Laboratory](https://huggingface.co/language-and-voice-lab). Most of the data is available at public repositories such as [LDC](https://www.ldc.upenn.edu/), [OpenSLR](https://openslr.org/) or [Clarin.is](https://clarin.is/)
+
+The specific list of corpora used to fine-tune the model is:
+
+- [Samrómur 21.05 (114h34m)](http://www.openslr.org/112/)
+- [Samrómur Children (127h25m)](https://catalog.ldc.upenn.edu/LDC2022S11)
+- [Malrómur (119hh03m)](https://clarin.is/en/resources/malromur/)
+- [Althingi Parliamentary Speech (514h29m)](https://catalog.ldc.upenn.edu/LDC2021S01)
+- L2-Speakers Data (125h55m) **Unpublished material**
+	
+The fine-tuning process was performed during March (2023) in the servers of the Language and Voice Laboratory (https://lvl.ru.is/) at Reykjavík University (Iceland) by Carlos Daniel Hernández Mena.
+
+# Evaluation
+```python
+import torch
+from transformers import WhisperForConditionalGeneration, WhisperProcessor
+
+#Load the processor and model.
+MODEL_NAME="carlosdanielhernandezmena/whisper-large-icelandic-10k-steps-1000h"
+processor = WhisperProcessor.from_pretrained(MODEL_NAME)
+model = WhisperForConditionalGeneration.from_pretrained(MODEL_NAME).to("cuda")
+
+#Load the dataset
+from datasets import load_dataset, load_metric, Audio
+ds=load_dataset("language-and-voice-lab/samromur_children",split='test')
+
+#Downsample to 16kHz
+ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
+
+#Process the dataset
+def map_to_pred(batch):
+	audio = batch["audio"]
+	input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features
+	batch["reference"] = processor.tokenizer._normalize(batch['normalized_text'])
+
+	with torch.no_grad():
+		predicted_ids = model.generate(input_features.to("cuda"))[0]
+	
+	transcription = processor.decode(predicted_ids)
+	batch["prediction"] = processor.tokenizer._normalize(transcription)
+	
+	return batch
+	
+#Do the evaluation
+result = ds.map(map_to_pred)
+
+#Compute the overall WER now.
+from evaluate import load
+
+wer = load("wer")
+WER=100 * wer.compute(references=result["reference"], predictions=result["prediction"])
+print(WER)
+```
+**Test Result**: 12.325364793542379
+
+# BibTeX entry and citation info
+*When publishing results based on these models please refer to:*
+```bibtex
+@misc{mena2023whisperlarge10kicelandic,
+      title={Acoustic Model in Icelandic: whisper-large-icelandic-10k-steps-1000h.}, 
+      author={Hernandez Mena, Carlos Daniel},
+      year={2023},
+      url={https://huggingface.co/carlosdanielhernandezmena/whisper-large-icelandic-10k-steps-1000h},
+}
+```
+
+# Acknowledgements
+
+Thanks to Jón Guðnason, head of the Language and Voice Lab for providing computational power to make this model possible. We also want to thank to the "Language Technology Programme for Icelandic 2019-2023" which is managed and coordinated by Almannarómur, and it is funded by the Icelandic Ministry of Education, Science and Culture.
+
+Special thanks to Björn Ingi Stefánsson for setting up the configuration of the server where this model was trained.
+