Downloads · 30 days
10
13% of all-time downloads
kaan84/whisper-sinhala-proto
whisper-sinhala-proto is a automatic speech recognition model from kaan84. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
whisper-sinhala-proto is an experimental Sinhala speech-recognition model based on OpenAI Whisper Small. The checkpoint is intended for early testing, benchmarking, and comparison during Sinhala ASR development.
Downloads · 30 days
10
13% of all-time downloads
All-time downloads
76
Public
Parameters
242M
1.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors967 MB · 99%
From the Hugging Face model README
whisper-sinhala-proto is an experimental Sinhala speech-recognition model based on OpenAI Whisper Small. The checkpoint is intended for early testing, benchmarking, and comparison during Sinhala ASR development.
This model appears to share the same base architecture, parameter count, task, and training-dataset tag as kaan84/whisper-small-sinhala-proto. If both repositories contain equivalent weights, consider keeping one as the canonical prototype and marking the other as archived or superseded to reduce user confusion.
| Item | Value |
|---|---|
| Task | Automatic speech recognition |
| Language | Sinhala (si) |
| Base model | openai/whisper-small |
| Model class | AutoModelForSpeechSeq2Seq |
| Parameters | Approximately 241.7M |
| Training dataset tag | large-sinhala-asr-dataset |
| Status | Experimental prototype |
from transformers import pipeline
transcriber = pipeline(
"automatic-speech-recognition",
model="kaan84/whisper-sinhala-proto",
)
result = transcriber(
"sample.wav",
generate_kwargs={"language": "si", "task": "transcribe"},
)
print(result["text"])
This prototype is not documented or evaluated sufficiently for high-impact production use.
To complete this model card, add:
openai/whisper-small modelThe model may hallucinate, omit, or incorrectly transcribe speech. Performance can vary with audio quality, noise, code-switching, accent, vocabulary, and speaker characteristics. Human review is necessary when accuracy matters.
Apache License 2.0. Confirm compatibility with the base-model license and every dataset or audio source used during fine-tuning.
kaan84/whisper-small-sinhala-v1kaan84/whisper-small-sinhala-proto