push model files

README.md

@@ -1,3 +1,124 @@
 ---
+language:
+- de
+thumbnail: null
+pipeline_tag: automatic-speech-recognition
+tags:
+- whisper
+- pytorch
+- speechbrain
+- Transformer
+- hf-asr-leaderboard
 license: apache-2.0
+datasets:
+- RescueSpeech
+metrics:
+- wer
+- cer
+model-index:
+- name: rescuespeech_whisper
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: RescueSpeech
+      config: de
+      split: test
+      args:
+        language: de
+    metrics:
+    - name: Test WER
+      type: wer
+      value: '23.14'
 ---
+
+<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
+<br/><br/>
+
+# Whisper large-v2 fine-tuned on RescueSpeech dataset.
+
+This repository provides all the necessary tools to perform automatic speech
+recognition from an end-to-end whisper model fine-tuned on the RescueSpeech dataset within
+SpeechBrain. For a better experience, we encourage you to learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+The performance of the model is the following:
+
+| Release | Test CER | Test WER | GPUs |
+|:-------------:|:--------------:|:--------------:| :--------:|
+| 01-07-23 | 10.82 |  23.14 | 1xA100 80 GB |
+
+## Pipeline description
+
+This ASR system is composed of whisper encoder-decoder blocks:
+- The pretrained whisper-large-v2 encoder is frozen.
+- The pretrained Whisper tokenizer is used.
+- A pretrained Whisper-large-v2 decoder ([openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2)) is finetuned on RescueSpeech dataset.
+The obtained final acoustic representation is given to the greedy decoder. 
+
+The system is trained with recordings sampled at 16kHz (single channel).
+The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *transcribe_file* if needed.
+
+## Install SpeechBrain
+
+First of all, please install tranformers and SpeechBrain with the following command:
+
+```
+pip install speechbrain transformers==4.26.0
+```
+
+Please notice that we encourage you to read our tutorials and learn more about
+[SpeechBrain](https://speechbrain.github.io).
+
+### Transcribing your own audio files (in French)
+
+```python
+
+from speechbrain.pretrained import WhisperASR
+
+asr_model = WhisperASR.from_hparams(source="speechbrain/rescuespeech_whisper", savedir="pretrained_models/rescuespeech_whisper")
+asr_model.transcribe_file("speechbrain/rescuespeech_whisper/example_de.wav")
+
+
+```
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
+
+You can find our training results (models, logs, etc) [here](https://www.dropbox.com/sh/45wk44h8e0wkc5f/AABjEJJJ_OJp2fDYz3zEihmPa?dl=0).
+
+### Limitations
+The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
+
+#### Referencing SpeechBrain
+
+```
+@misc{SB2021,
+    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
+    title = {SpeechBrain},
+    year = {2021},
+    publisher = {GitHub},
+    journal = {GitHub repository},
+    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
+  }
+```
+
+### Referencing RescueSpeech
+```bibtex
+@misc{sagar2023rescuespeech,
+    title={RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain},
+    author={Sangeet Sagar and Mirco Ravanelli and Bernd Kiefer and Ivana Kruijff Korbayova and Josef van Genabith},
+    year={2023},
+    eprint={2306.04054},
+    archivePrefix={arXiv},
+    primaryClass={eess.AS}
+}
+```
+
+#### About SpeechBrain
+SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains.
+
+Website: https://speechbrain.github.io/
+
+GitHub: https://github.com/speechbrain/speechbrain

hyperparams.yaml

@@ -0,0 +1,68 @@
+# Generated 2023-06-24 from:
+# /netscratch/sagar/thesis/speechbrain/recipes/RescueSpeech/ASR/transformer/hparams/train_hf_whisper.yaml
+# yamllint disable
+# ################################
+# Model: Whisper (Encoder-Decoder) + NLL
+# Augmentation: TimeDomainSpecAugment
+# Authors: Sangeet Sagar 2022
+# ################################
+
+
+# URL for the biggest Fairseq english whisper model.
+whisper_hub: openai/whisper-large-v2
+language: german
+
+# Normalize the english inputs with
+# the same normalization done in the paper
+normalized_transcripts: true
+test_only: false # Set it to True if you only want to  do the evaluation
+
+auto_mix_prec: false
+sample_rate: 16000
+
+# These values are only used for the searchers.
+# They needs to be hardcoded and should not be changed with Whisper.
+# They are used as part of the searching process.
+# The bos token of the searcher will be timestamp_index
+# and will be concatenated with the bos, language and task tokens.
+timestamp_index: 50363
+eos_index: 50257
+bos_index: 50258
+
+# Decoding parameters
+min_decode_ratio: 0.0
+max_decode_ratio: 1.0
+test_beam_size: 8
+
+# Model parameters
+freeze_whisper: false
+freeze_encoder_only: false
+freeze_encoder: true
+
+#
+# Functions and classes
+#
+whisper: &id001 !new:speechbrain.lobes.models.huggingface_whisper.HuggingFaceWhisper
+  source: openai/whisper-large-v2/
+  freeze: false
+  save_path: openai/whisper-large-v2/
+  encoder_only: false
+  freeze_encoder: true
+
+
+modules:
+  whisper: *id001
+whisper_opt_class: !name:torch.optim.AdamW
+  lr: 0.00003
+  weight_decay: 0.01
+
+decoder: !new:speechbrain.decoders.seq2seq.S2SWhisperGreedySearch
+  model: *id001
+  bos_index: 50363
+  eos_index: 50257
+  min_decode_ratio: 0.0
+  max_decode_ratio: 1.0
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+  loadables:
+    whisper: !ref <whisper>

whisper.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed33c072cfd8f184b189375df94e587df7afac08d65106b9ad42a761df14b65c
+size 6173767281