GigaAM v2 models converted to ONNX format for onnx-asr.
Install onnx-asr
pip install onnx-asr[cpu,hub]
Load GigaAM v2 CTC model and recognize wav file
import onnx_asr
model = onnx_asr.load_model("gigaam-v2-ctc")
print(model.recognize("test.wav"))
Load GigaAM v2 RNN-T model and recognize wav file
import onnx_asr
model = onnx_asr.load_model("gigaam-v2-rnnt")
print(model.recognize("test.wav"))
Code for models export
import gigaam
from pathlib import Path
onnx_dir = "gigaam-onnx"
model_type = "rnnt" # or "ctc"
model = gigaam.load_model(
model_type,
fp16_encoder=False, # only fp32 tensors
use_flash=False, # disable flash attention
)
model.to_onnx(dir_path=onnx_dir)
with Path(onnx_dir, "v2_vocab.txt").open("wt") as f:
for i, token in enumerate(["\u2581", *(chr(ord("а") + i) for i in range(32)), "<blk>"]):
f.write(f"{token} {i}\n")