library_name: transformers
tags: []
Model Card for Model ID
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub.
- Developed by: [Fastino Mateteva]
- Model type: [Transformer model]
- Language(s) (NLP): [Shona]
- License: []
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[### Running the model
Click to expand
```python!pip install transformers datasets torchaudio
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor import torch import torchaudio
model_id = "fastinom/ASR_fassy"
Load model and processor
model = Wav2Vec2ForCTC.from_pretrained(model_id) processor = Wav2Vec2Processor.from_pretrained(model_id)
def load_audio(file_path): speech_array, sampling_rate = torchaudio.load(file_path) resampler = torchaudio.transforms.Resample(sampling_rate, 16000) speech = resampler(speech_array).squeeze().numpy() return speech
Example audio file path
audio_file = "/content/drive/MyDrive/recordings/wavefiles/1.wa"#YOUR AUDIO PATH speech = load_audio(audio_file)
Preprocess the audio
inputs = processor(speech, sampling_rate=16000, return_tensors="pt", padding=True)
Perform inference
with torch.no_grad(): logits = model(inputs.input_values).logits
Decode the output
predicted_ids = torch.argmax(logits, dim=-1) transcription = processor.batch_decode(predicted_ids) print(transcription[0])
</details>]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-4
- per_device_train_batch_size=4
- eval_batch_size: 2
- evaluation_strategy="steps"
- gradient_checkpointing=True
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- num_train_epochs=3
- save_total_limit=1
- fp16=True
- save_steps=400
- eval_steps=200
- logging_steps=200
- push_to_hub=True
### Training results
| Training Loss | WER | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 6.427 | 1.00 | 200 | 4.1518 |
| 3.7979 | 1.00 | 400 | 3.8410 |
| 3.6924 | 1.00 | 600 | 3.4249 |
| 0.8357 | 0.26 | 800 | 0.2396 |
| 0.1528 | 0.24 | 1000 | 0.2155 |
| 0.1415 | 0.24 | 1200 | 0.2036 |
| 0.1278 | 0.24 | 1400 | 0.2028 |
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be 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).
- **Hardware Type:** [T4 GPU]
- **Hours used:** [3]
- **Cloud Provider:** [Google Colab]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Model Card Authors [optional]
[Fastino Mateteva]
## Model Card Contact
[fastinomateteva@gmail.com]