Reza2kn/visualears-fastconformer-fa-full-ab-litert-fp16

VisualEars FastConformer Persian ASR LiteRT FP16

LiteRT/TFLite FP16 fixed-length acoustic CTC-core export of Reza2kn/visualears-fastconformer-fa-full-ab.

Artifact

• Format: LiteRT/TFLite fixed-length acoustic CTC-core export
• File: fastconformer_ctc_fixed2005_float16_fc.tflite
• Quantization: ai_edge_quantizer float_casting, bits=16, dtype=FLOAT
• Quantized op family: FULLY_CONNECTED
• Minimum weight elements: 250000
• Runtime validation: LiteRT/TFLite XNNPACK CPU
• Size: 256,460,656 bytes, 58.65% of the FP32 LiteRT baseline

Validation

Check	Result
16-item frame-level CTC argmax parity vs FP32 LiteRT	100.00%
16-item exact transcript parity vs FP32 LiteRT	16 / 16
VisualEars269 browser-feature exact transcript parity vs FP32 LiteRT	269 / 269
VisualEars269 browser-feature normalized transcript parity vs FP32 LiteRT	269 / 269

The VisualEars269 check uses browser-style 80-bin log-mel features matching the real-time browser demo feature path, then compares greedy CTC-collapsed transcripts from this FP16 LiteRT model against the FP32 LiteRT baseline.

Usage Boundary

This is a fixed-frame feature-to-logits CTC core. It takes precomputed log-mel features shaped [1, 80, 2005] as processed_signal; it is not a full raw-audio-to-text pipeline by itself.

Files

• fastconformer_ctc_fixed2005_float16_fc.tflite: FP16 LiteRT model.
• recipe.json: ai_edge_quantizer recipe.
• validation/litert_float16_summary.json: size and 16-item frame-argmax parity.
• validation/litert_fp16_vs_fp_transcript_parity.json: 16-item transcript parity.
• validation/litert_fp16_vs_fp_visualears269_browser_features_transcript_parity.json: 269-item transcript parity.
• validation/visualears_benchmark_269_browser_features.json: feature-generation metadata for the 269 check.