Update README.md

README.md

@@ -13,14 +13,13 @@ tags:
   - streaming
 datasets:
   - alexandrainst/coral
-  - mozilla-foundation/common_voice_17_0
 library_name: transformers
 pipeline_tag: automatic-speech-recognition
 metrics:
   - wer
   - cer
 model-index:
-  - name: hvisketiske-v2
+  - name: milo-asr
     results:
       - task:
           type: automatic-speech-recognition
@@ -38,9 +37,9 @@ model-index:
             name: CER
 ---
 
-# hvisketiske-v2: Danish ASR Model
+# Milo-ASR: Dansk ASR Model
 
-**hvisketiske-v2** is a state-of-the-art Danish automatic speech recognition (ASR) model based on [Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B), finetuned on the [CoRal v2 dataset](https://huggingface.co/datasets/alexandrainst/coral) for improved Danish transcription accuracy.
+**Milo-ASR** er en "state of the art" Dansk automatic speech recognition (ASR) model baseret på [Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B), finetuned på  [CoRal v2 dataset](https://huggingface.co/datasets/alexandrainst/coral) for at gøre den bedre til at forstå dansk.
 
 ## Key Highlights
 
@@ -51,13 +50,13 @@ model-index:
 | **Real-Time Factor** | 0.086 (45% faster than Whisper v3) |
 | **Model Size** | ~1.7B parameters |
 
-### Inherited Features from Qwen3-ASR
+### Fordele nedarvet fra Qwen3-ASR
 
 - **Streaming/Real-time transcription** via vLLM backend
-- **Singing detection** - can transcribe singing voice and songs with BGM
+- **Sang detection** - Til at kunne transskribere teksten fra lyde med baggrundsmusik (find ud af hvad Rasmus seebach synger 🤣)
 - **Word-level timestamps** via forced alignment
 - **30+ language support** (Danish optimized)
-- **Long audio support** - up to 20 minutes per request
+- **20 minutter pr. request** - Kan kører 20 minutter igennem pr. kald
 
 ---
 
@@ -67,7 +66,7 @@ model-index:
 
 | Model | WER | CER | RTF | Throughput | Parameters |
 |-------|-----|-----|-----|------------|------------|
-| **hvisketiske-v2** | **18.47%** | **7.86%** | **0.086** | 1.71 samples/s | ~1.7B |
+| **Milo-ASR** | **18.47%** | **7.86%** | **0.086** | 1.71 samples/s | ~1.7B |
 | hviske-v3 (Whisper Large v3) | 21.47% | 8.79% | 0.156 | 0.94 samples/s | ~2B |
 
 **Improvements over Whisper Large v3:**
@@ -99,7 +98,7 @@ from qwen_asr import Qwen3ASRModel
 
 # Load the model
 model = Qwen3ASRModel.from_pretrained(
-    "pluttodk/hvisketiske-v2",
+    "pluttodk/Milo-ASR",
     dtype="bfloat16",
     device_map="cuda:0",
 )
@@ -125,7 +124,7 @@ Process multiple audio files efficiently in a single call:
 from qwen_asr import Qwen3ASRModel
 
 model = Qwen3ASRModel.from_pretrained(
-    "pluttodk/hvisketiske-v2",
+    "pluttodk/Milo-ASR",
     dtype="bfloat16",
     device_map="cuda:0",
     max_inference_batch_size=16,  # Process up to 16 files at once
@@ -150,7 +149,7 @@ Get word-level timestamps using the forced aligner:
 from qwen_asr import Qwen3ASRModel
 
 model = Qwen3ASRModel.from_pretrained(
-    "pluttodk/hvisketiske-v2",
+    "pluttodk/Milo-ASR",
     forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
     dtype="bfloat16",
     device_map="cuda:0",
@@ -176,7 +175,7 @@ from qwen_asr import Qwen3ASRModel
 
 # Initialize with vLLM backend for streaming
 model = Qwen3ASRModel.LLM(
-    model="pluttodk/hvisketiske-v2",
+    model="pluttodk/Milo-ASR",
     gpu_memory_utilization=0.8,
 )
 
@@ -215,13 +214,13 @@ import librosa
 
 # Load model and processor
 model = AutoModel.from_pretrained(
-    "pluttodk/hvisketiske-v2",
+    "pluttodk/Milo-ASR",
     trust_remote_code=True,
     torch_dtype=torch.bfloat16,
     device_map="cuda:0",
 )
 processor = AutoProcessor.from_pretrained(
-    "pluttodk/hvisketiske-v2",
+    "pluttodk/Milo-ASR",
     trust_remote_code=True,
 )
 
@@ -262,7 +261,7 @@ The model inherits Qwen3-ASR's ability to handle singing and background music:
 from qwen_asr import Qwen3ASRModel
 
 model = Qwen3ASRModel.from_pretrained(
-    "pluttodk/hvisketiske-v2",
+    "pluttodk/Milo-ASR",
     dtype="bfloat16",
     device_map="cuda:0",
 )
@@ -282,7 +281,7 @@ print(results[0].text)
 
 ### Model Description
 
-hvisketiske-v2 is a Danish-specialized automatic speech recognition model created by finetuning [Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) on the [CoRal v2 dataset](https://huggingface.co/datasets/alexandrainst/coral). The model achieves state-of-the-art performance on Danish speech recognition while maintaining fast inference speeds.
+Milo-ASR is a Danish-specialized automatic speech recognition model created by finetuning [Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) on the [CoRal v2 dataset](https://huggingface.co/datasets/alexandrainst/coral). The model achieves state-of-the-art performance on Danish speech recognition while maintaining fast inference speeds.
 
 - **Developed by:** Mathias Oliver Valdbjørn Rønnelund
 - **Model type:** Encoder-decoder speech recognition model
@@ -366,45 +365,22 @@ Evaluated on the CoRal v2 test split:
 
 | Model | WER | CER | RTF | Throughput |
 |-------|-----|-----|-----|------------|
-| **hvisketiske-v2** | **18.47%** | **7.86%** | **0.086** | 1.71 samples/sec |
+| **Milo-ASR** | **18.47%** | **7.86%** | **0.086** | 1.71 samples/sec |
 | hviske-v3 (Whisper v3) | 21.47% | 8.79% | 0.156 | 0.94 samples/sec |
 
 ---
 
-## Limitations
-
-- **Language:** Optimized for Danish; other languages may have degraded performance compared to base Qwen3-ASR
-- **Audio quality:** Best results with clear speech; noisy environments may affect accuracy
-- **Domain:** Trained on CoRal v2 which is primarily conversational/read-aloud speech; specialized domains (medical, legal, technical) may have higher error rates
-- **Streaming:** Real-time streaming requires vLLM backend installation
-
-## Intended Use
-
-### Primary Use Cases
-- Danish speech-to-text transcription
-- Subtitle generation for Danish content
-- Voice assistant backends
-- Meeting transcription
-- Accessibility applications
-
-### Out-of-Scope Use
-- Non-Danish languages (use base Qwen3-ASR instead)
-- Real-time speaker diarization (not supported)
-- Emotion/sentiment detection from speech
-
----
-
 ## Citation
 
 If you use this model, please cite:
 
 ```bibtex
-@misc{hvisketiske-v2,
+@misc{Milo-ASR,
   author = {Rønnelund, Mathias Oliver Valdbjørn},
-  title = {hvisketiske-v2: Danish ASR Model based on Qwen3-ASR},
+  title = {Milo-ASR: Danish ASR Model based on Qwen3-ASR},
   year = {2025},
   publisher = {HuggingFace},
-  url = {https://huggingface.co/pluttodk/hvisketiske-v2}
+  url = {https://huggingface.co/pluttodk/Milo-ASR}
 }
 ```
 
@@ -430,5 +406,5 @@ Also consider citing the base model and dataset:
 
 ## Acknowledgements
 
-- [Qwen Team](https://github.com/QwenLM) for the excellent Qwen3-ASR base model
-- [Alexandra Institute](https://alexandra.dk/) for the CoRal v2 Danish speech corpus
+- [Qwen Team](https://github.com/QwenLM) for Qwen3-ASR base model
+- [Alexandra Institute](https://alexandra.dk/) for CoRal v2 lyd corpus