update model card README.md

README.md

@@ -1,61 +1,53 @@
 ---
 license: apache-2.0
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
-- google/fleurs
+- fleurs
 metrics:
 - wer
 model-index:
-- name: Whisper Small Amharic FLEURS
+- name: whisper-small-amet
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: google/fleurs am_et
-      type: google/fleurs
+      name: fleurs
+      type: fleurs
       config: am_et
-      split: test+validation
+      split: validation
       args: am_et
     metrics:
     - name: Wer
       type: wer
-      value: 160.99
-language:
-- amh 
+      value: 100.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
+# whisper-small-amet
 
-# Whisper Small Tamil FLEURS
-
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs am_et dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the fleurs dataset.
 It achieves the following results on the evaluation set:
-- Loss: -
-- Wer: 160.99
+- Loss: 6.8012
+- Wer: 100.0
 
 ## Model description
 
-- The main Whisper Small Hugging Face page: [Hugging Face - Whisper Small](https://huggingface.co/openai/whisper-small)
+More information needed
 
 ## Intended uses & limitations
 
-- For experimentation and curiosity. 
-- Based on the paper [AXRIV](https://arxiv.org/abs/2212.04356) and [Benchmarking OpenAI Whisper for non-English ASR - Dan Shafer](https://blog.deepgram.com/benchmarking-openai-whisper-for-non-english-asr/), there is a performance bias towards certain languages and curated datasets.
-- From the Whisper paper, am_et is a low resource language (Table E), with the WER results ranging from 120-229, based on model size. Whisper small WER=120.2, indicating more training time may improve the fine tuning.
+More information needed
 
 ## Training and evaluation data
 
-- This model was trained/evaluated on "test+validation" data from google/fleurs [google/fluers - HuggingFace Datasets](https://huggingface.co/datasets/google/fleurs).
+More information needed
 
 ## Training procedure
 
-- The training was done in Lambda Cloud GPU on A100/40GB GPUs, which were provided by OpenAI Community Events [Whisper Fine Tuning Event - Dec 2022](https://github.com/huggingface/community-events/tree/main/whisper-fine-tuning-event#fine-tune-whisper). The training was done using [HuggingFace Community Events - Whisper - run_speech_recognition_seq2seq_streaming.py](https://github.com/huggingface/community-events/blob/main/whisper-fine-tuning-event/run_speech_recognition_seq2seq_streaming.py) using the included [whisper_python_am_et.ipynb](https://huggingface.co/drmeeseeks/whisper-small-am_et/blob/main/am_et_fine_tune_whisper_streaming_colab_RUNNING-evalerrir.ipynb) to setup the Lambda Cloud GPU/Colab environment. For Colab, you must reduce the train batch size to the recommended amount mentioned at , as the T4 GPUs have 16GB of memory [Whisper Fine Tuning Event - Dec 2022](https://github.com/huggingface/community-events/tree/main/whisper-fine-tuning-event#fine-tune-whisper). The notebook sets up the environment, logs into your huggingface account, and generates a bash script. The bash script generated in the IPYNB, `run.sh` was run from the terminal to train `bash run.sh`, as described on the Whisper community events GITHUB page. Num Examples = 446, Num Epochs = 715, Number of trainable parameters = 241734912.
-
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -63,88 +55,41 @@ The following hyperparameters were used during training:
 - train_batch_size: 64
 - eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 1
-- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 1000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
-- do_eval=False
-
 
 ### Training results
 
-5000 Steps
-
-| Training Loss | Epoch | Step | Learning Rate |
-|:-------------:|:-----:|:-----:|:-----:|
-| 3.0968        | 0.05 | - | 4.2e-7 |
-| 1.178        | 28.57 | - | 3.92e-6 |
-| 0.03        | 53.57 | - | 7.42e-6 |
-| 0.0002        | 217.86 | - | 7.73e-6 |
-| 0.0001        | 378.57 | ~ 2000 | 5.23e-6 |
-| 0.0000        | 382.14 | - | 5.14e-6 |
-| 0.0000        | 467.86 | 3300 | 3.84e-6|
-| 0.0000        | 614.29 | 4300 | 1.56e-6|
-| 0.0000        | 685.71 | 4812 | 4.53e-7|
-| 0.0000        | 710.71 | 4997 | 6.44e-8|
-
-3000 Steps
-
-| Training Loss | Epoch | Step | Learning Rate |
-|:-------------:|:-----:|:-----:|:-----:|
-| 3.0968        | 0.05 | - | 4.2e-7 |
-| 0.0017        | 96.43 | 687 | 9.316e-6 |
-
-
-### Recommendations 
-
-Limit training duration for smaller datasets to ~ 2000 to 3000 steps to avoid overfitting. 5000 steps using the [HuggingFace - Whisper Small](https://huggingface.co/openai/whisper-small) takes ~ 5hrs on A100 GPUs (1hr/1000 steps). Encountered `RuntimeError: The size of tensor a (504) must match the size of tensor b (448) at non-singleton dimension 1` which is related to [Trainer RuntimeError](https://discuss.huggingface.co/t/trainer-runtimeerror-the-size-of-tensor-a-462-must-match-the-size-of-tensor-b-448-at-non-singleton-dimension-1/26010) as some languages datasets have input lengths that have non-standard lengths. The link did not resolve my issue, and appears elsewhere too [Training languagemodel – RuntimeError the expanded size of the tensor (100) must match the existing size (64) at non singleton dimension 1](https://hungsblog.de/en/technology/troubleshooting/training-languagemodel-runtimeerror-the-expanded-size-of-the-tensor-100-must-match-the-existing-size-64-at-non-singleton-dimension-1/). To circumvent this issue, `run.sh` only trains and saves the model (if you make changes to `run.sh` be sure to clear/rm the contents as piping appends). Then run `python run_eval_whisper_streaming.py --model_id="openai/whisper-small" --dataset="google/fleurs" --config="am_et" --batch_size=32 --max_eval_samples=64 --device=0 --language="am"` to find the WER score. Erroring out during evaluation prevents the trained model from loading to HugginFace. Based on the paper [AXRIV](https://arxiv.org/abs/2212.04356) and [Benchmarking OpenAI Whisper for non-English ASR - Dan Shafer](https://blog.deepgram.com/benchmarking-openai-whisper-for-non-english-asr/), there is a performance bias towards certain languages and curated datasets. The OpenAI fintuning community event provided ample _free_ GPU time to help develop the model further and improve WER scores.
-
-### Environmental Impact
-
-Carbon emissions were estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). In total roughly 100 hours were used primarily in US East/Asia Pacific (80%/20%), with AWS as the reference. Additional resources are available at [Our World in Data - CO2 Emissions](https://ourworldindata.org/co2-emissions) 
-
-- __Hardware Type__: AMD EPYC 7J13 64-Core Processor (30 core VM) 197GB RAM, with NVIDIA A100-SXM 40GB
-- __Hours Used__: 100 hrs
-- __Cloud Provider__: Lambda Cloud GPU 
-- __Compute Region__: US East/Asia Pacific
-- __Carbon Emitted__: 12 kg (GPU) + 13 kg (CPU) = 25 kg (the weight of 3 gallons of water)
-
-
-### Citation
-
-- [Whisper - GITHUB](https://github.com/openai/whisper)
-- [Whisper - OpenAI - BLOG](https://openai.com/blog/whisper/)
-- [Model Card - HuggingFace Hub - GITHUB](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md)
-
-```bibtex
-@misc{https://doi.org/10.48550/arxiv.2212.04356,
-  doi = {10.48550/ARXIV.2212.04356},
-  url = {https://arxiv.org/abs/2212.04356},
-  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
-  keywords = {Audio and Speech Processing (eess.AS), Computation and Language (cs.CL), Machine Learning (cs.LG), Sound (cs.SD), FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Computer and information sciences, FOS: Computer and information sciences},
-  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
-  publisher = {arXiv},
-  year = {2022},
-  copyright = {arXiv.org perpetual, non-exclusive license}
-}
-
-@article{owidco2andothergreenhousegasemissions,
-    author = {Hannah Ritchie and Max Roser and Pablo Rosado},
-    title = {CO₂ and Greenhouse Gas Emissions},
-    journal = {Our World in Data},
-    year = {2020},
-    note = {https://ourworldindata.org/co2-and-other-greenhouse-gas-emissions}
-}
-
-```
+| Training Loss | Epoch  | Step | Validation Loss | Wer      |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.9013        | 100.0  | 100  | 2.7051          | 276.0    |
+| 0.0002        | 200.0  | 200  | 3.7415          | 334.6667 |
+| 0.0001        | 300.0  | 300  | 3.8402          | 117.3333 |
+| 0.0001        | 400.0  | 400  | 3.8931          | 340.0    |
+| 0.0001        | 500.0  | 500  | 4.0671          | 397.3333 |
+| 0.0001        | 600.0  | 600  | 4.2844          | 137.3333 |
+| 0.0           | 700.0  | 700  | 4.4697          | 289.3333 |
+| 0.0           | 800.0  | 800  | 4.6278          | 449.3333 |
+| 0.0           | 900.0  | 900  | 4.7794          | 678.6667 |
+| 0.0405        | 1000.0 | 1000 | 4.6769          | 261.3333 |
+| 0.0002        | 1100.0 | 1100 | 5.4995          | 100.0    |
+| 0.0002        | 1200.0 | 1200 | 6.0033          | 100.0    |
+| 0.0002        | 1300.0 | 1300 | 6.2884          | 100.0    |
+| 0.0002        | 1400.0 | 1400 | 6.4744          | 100.0    |
+| 0.0002        | 1500.0 | 1500 | 6.5964          | 100.0    |
+| 0.0001        | 1600.0 | 1600 | 6.6792          | 100.0    |
+| 0.0001        | 1700.0 | 1700 | 6.7370          | 100.0    |
+| 0.0001        | 1800.0 | 1800 | 6.7735          | 100.0    |
+| 0.0001        | 1900.0 | 1900 | 6.7958          | 100.0    |
+| 0.0001        | 2000.0 | 2000 | 6.8012          | 100.0    |
 
 
 ### Framework versions
 
 - Transformers 4.26.0.dev0
-- Pytorch 1.13.0+cu117
-- Datasets 2.7.1.dev0
+- Pytorch 1.13.1+cu117
+- Datasets 2.8.1.dev0
 - Tokenizers 0.13.2