Update README.md

README.md

@@ -39,3 +39,60 @@ model-index:
       type: cer
       value: 3.194
 ---
+
+
+# Whisper-medium-et
+
+This is a Whisper-medium model [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) finetuned on around 800 hours of diverse Estonian data.
+
+## Model description
+This is a general-purpose Estonian ASR model trained in the Lab of Language Technology at TalTech.
+
+
+## Intended uses & limitations
+
+This model is intended for general-purpose speech recognition, such as broadcast conversations, interviews, talks, etc.
+
+## How to use
+
+Use as any other Whisper model via HF transformers, or use a faster decoder like [faster-whisper](https://github.com/guillaumekln/faster-whisper).
+
+
+#### Limitations and bias
+
+Since this model was trained on mostly broadcast speech and texts from the web, it might have problems correctly decoding the following:
+  * Speech containing technical and other domain-specific terms
+  * Children's speech
+  * Non-native speech
+  * Speech recorded under very noisy conditions or with a microphone far from the speaker
+  * Very spontaneous and overlapping speech
+
+## Training data
+Acoustic training data:
+
+| Type                  | Amount (h) |
+|-----------------------|:------:|
+| Broadcast speech      |   591  |
+| Spontaneous speech    |   53   |
+| Elderly speech corpus |   53   |
+| Talks, lectures       |   49   |
+| Parliament speeches   |   31   |
+| *Total*               |   *761*  |
+
+
+
+## Training procedure
+
+Finetuned using Espnet, and then comverted to transformers format using [this](https://gist.github.com/alumae/2dcf473b667cec9d513b80ea24e94672) script. 
+Finetuning procedure is similar to [this](https://huggingface.co/espnet/shihlun_asr_whisper_medium_finetuned_librispeech100) model.
+
+## Evaluation results
+
+### WER
+
+WER results below are obtained using greedy decoding (i.e., beam size 1).
+
+|Dataset | WER |
+|---|---|
+| Common Voice 8.0 | 13.8 |
+| Common Voice 11.0 | 14.7 |