Update README.md

README.md

@@ -6,4 +6,90 @@ base_model:
 - openai/whisper-large-v3-turbo
 pipeline_tag: automatic-speech-recognition
 library_name: transformers
----
+---
+
+
+## Introduction
+
+This model is OpenAI Whisper large-v3-turbo, finetuned on 1400 hours of audio with manually created verbatim transcriptions from the TalTech Estonian Speech Dataset 1.0 (https://cs.taltech.ee/staff/tanel.alumae/data/est-pub-asr-data/).
+
+## Usage
+
+It's a finetuned vesion of Whisper large-v3-turbo and can be therefore used via Hugging Face 🤗 Transformers. To run the model, first install the Transformers
+library. For this example, we'll also install 🤗 Accelerate to reduce the model loading time:
+
+```bash
+pip install --upgrade pip
+pip install --upgrade transformers accelerate
+```
+
+The model can be used with the [`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
+class to transcribe audios of arbitrary length:
+
+```python
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+from datasets import load_dataset
+
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model_id = "TalTechNLP/whisper-large-v3-turbo-et-verbatim"
+
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
+)
+model.to(device)
+
+processor = AutoProcessor.from_pretrained(model_id)
+
+pipe = pipeline(
+"automatic-speech-recognition",
+model=model,
+tokenizer=processor.tokenizer,
+feature_extractor=processor.feature_extractor,
+torch_dtype=torch_dtype,
+device=device,
+)
+
+audio = "sample.mp3"
+
+result = pipe(sample, generate_kwargs={"task": "transcribe", "language": "et"})
+print(result)
+```
+
+There is a also a ct2 verison of the model that can be used with tools that a based on `faster-whisper`, e.g. using the `whisper-ctranslate2` command line program, e.g.:
+
+```
+$ whisper-ctranslate2 --model_directory ct2 --language et --vad_filter True --threads 8 --output_dir demo demo/etteütlus2024.wav
+Detected language 'Estonian' with probability 1.000000
+[00:00.620 --> 00:08.820] Kas pole teps mitte kihvt, et Haridus- ja Teadusministeerium paikneb Tartus Munga tänaval?
+[00:08.820 --> 00:23.420] Seal ülikooli peahoonest mõne kukesammu kaugusel tuleb pedagoogikaalased otsused langetada kevisse raiutud imposantsete kultuuriheeroste märksa pilgu all.
+[00:23.420 --> 00:32.680] Peeter Põllu esimese haridusministri rühikas selg tuletab meelde koolmeistrite määravat osatähtsust ühiskonnas.
+[00:32.680 --> 00:45.140] Ning üksi silmi teineteist jälgivad Kreutzwald ja Kalevipoeg kõrvu Oskar Lutsuliku kaine literaadi pilguga ei lase unustada Eesti vaimuilma alusväärtusi.
+[00:45.140 --> 00:52.640] Vahest peaks valitsusegi Stenbocki majast rahvusülikooli akadeemilisse mõju välja kupattama.
+[00:52.640 --> 01:05.860] Nii oleks võimukandjatel ehk mahti ilmavaate turgutamiseks linnaraamatukogust kübekene tarkust nõutada või Tartu Kunstimuuseumis kultustaieseid nautida.
+[01:05.860 --> 01:17.500] Too piisatorni sarnane majamürakas võib tekitada muidugi äraspidise tunde, et Emajõe ja Ateenas on alalõpmata midagi viltu.
+Transcription results written to 'demo' directory
+
+```
+
+## Citation
+
+```
+@inproceedings{alumae-etal-2023-automatic,
+title = "Automatic Closed Captioning for {E}stonian Live Broadcasts",
+author = {Alum{\"a}e, Tanel and
+Kalda, Joonas and
+Bode, K{\"u}lliki and
+Kaitsa, Martin},
+booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
+month = may,
+year = "2023",
+address = "T{\'o}rshavn, Faroe Islands",
+publisher = "University of Tartu Library",
+url = "https://aclanthology.org/2023.nodalida-1.49",
+pages = "492--499"
+}
+```