Model reference · open weights
wav2vec2-large-xls-r-Urdu is an open-weight audio or speech model from kingabzpro, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Urdu ASR XLS-R 300M A fine-tuned XLS-R 300M CTC model for Urdu automatic speech recognition. It transcribes 16 kHz mono audio and includes an optional 5-gram KenLM decoder. Best reported result: 39.89% WER / 16.70% CER with KenLM decoding on the Urdu Common Voice 8.0 test set. See the Kaggle evaluation notebook for a reproducible example. ⚡ Quick start Install the required packages: Note: After installing the packages in a notebook environment, restart the kernel before running the inference code. Transcribe a local audio file: 🧠 Language-model decoding Why use it? The included 5-gram KenLM language model reduces the reported full-test WER from 56.07% (greedy CTC) to 39.89%. The repository contains a 5-gram KenLM language model. 🧪 Kaggle evaluation The Kaggle notebook evaluates a five-sample streaming smoke test from fixie-ai/commonvoice170 (ur, test). Recorded notebook output Single-sample inference: Five-sample streaming smoke-test results: Important: This is a five-sample smoke test—not a benchmark. Do not compare it directly with the full Common Voice 8.0 test-set results below. 📊 Evaluation Full Common Voice 8.0 test set Results are reported on the Urdu test split of Mozilla Common Voice 8.0. The language-model row is the model-card score; compare each result only with the same decoding strategy. To reproduce language-model evaluation from this repository: 🏗️ Training The model was trained from facebook/wav2vec2-xls-r-300m on Urdu Mozilla Common Voice 8.0. ⚠️ Intended use and limitations Use this model for Urdu speech transcription and prototyping. Accuracy varies with recording quality, speaker accent, code-switching, background noise, domain-specific vocabulary, and utterance length. Review transcripts before using them in consequential or user-facing workflows. - Transformers 4.17.0.dev0 - PyTorch 1.10.2+cu102 - Datasets 1.18.2.dev0 - Tokenizers 0.11.0
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | kingabzpro |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 315M |
| Variants | 1 |
| Runs with | transformers |
| Based on | facebook/wav2vec2-xls-r-300m |
| Released | 2022-03-02 |
| Popularity | 1.3M downloads / month |
| Likes | 14 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| wav2vec2-large-xls-r-300m-Urdu | 315M | BF16 | ~0.7 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Speech Recognition | Common Voice 8 | Test WER | 39.89 |
| Speech Recognition | Common Voice 8 | Test CER | 16.7 |
Using it via the API
Once AxForge deploys wav2vec2-large-xls-r-urdu for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xls-r-urdu below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="wav2vec2-large-xls-r-urdu" -F file=@audio.mp3
Details
Languages
Trained / evaluated on
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗