Parseh aligner tr v1: ONNX int8 from mpoyraz/wav2vec2-xls-r-300m-cv7-turkish@708639f50559d7970f462e13ec64d3f059ca89f6
fc4d78d verified | license: cc-by-4.0 | |
| language: tr | |
| library_name: onnx | |
| tags: | |
| - onnx | |
| - wav2vec2 | |
| - ctc | |
| - forced-alignment | |
| - quantized | |
| - parseh | |
| base_model: mpoyraz/wav2vec2-xls-r-300m-cv7-turkish | |
| base_model_relation: quantized | |
| datasets: | |
| - common_voice_7_0 | |
| - mediaspeech | |
| # Parseh Turkish forced-alignment network | |
| This CTC network aligns known Turkish caption text to 16 kHz mono audio in Parseh. It is not a general-purpose speech-recognition model. Parseh runs it locally with NumPy and ONNX Runtime, then uses CTC Viterbi alignment for word spans or character spans. | |
| ## Provenance and conversion | |
| Derived from [mpoyraz/wav2vec2-xls-r-300m-cv7-turkish](https://huggingface.co/mpoyraz/wav2vec2-xls-r-300m-cv7-turkish) at `708639f50559d7970f462e13ec64d3f059ca89f6`, based on `facebook/wav2vec2-large-xls-r-300m`. It was converted to ONNX opset 17 and dynamically quantized to int8 (`QUInt8`, per-channel `MatMul` weights); no retraining was performed. Exact source and output hashes are in `meta.json` and `SHA256SUMS`. | |
| ## Verification | |
| - ONNX Runtime CPU versions: 1.23.2, 1.30.0; dynamic 0.5 s and 60 s inputs passed. | |
| - fp32 ONNX/PyTorch log-softmax max absolute difference: `9.5367431640625e-06`; frame-argmax agreement: `None`. | |
| - int8/fp32 frame-argmax agreement: `1.0`; generated-speech span-start delta median/p95/max: `0.0` / `0.0` / `0.0` ms. | |
| - Generated 30-second CPU alignment cost: `6.663475` s; peak RSS: `2870992896` bytes. | |
| `espeak-ng` generated audio was used only for pipeline monotonicity, not a real-speech accuracy claim. Unknown characters use a wildcard score to preserve a monotonic path. | |
| ## Limitations | |
| Input must be 16 kHz mono audio and known caption text. Noise, accents, text errors, vocabulary gaps, and quantization can affect timestamps. No accuracy guarantee is made. | |
| ## Licence and attribution | |
| The source tag is `cc-by-4.0`. `LICENSE` and `NOTICE` retain source, base-model, dataset attribution, and changes. No endorsement by original authors, Meta, Mozilla, or Parseh is implied. | |
| ## Citation from the source card | |
| No separate citation block was provided by the source card. | |
| ## Contact | |
| Contact: [development@parseh.io](mailto:development@parseh.io). | |