| | |
|---|
| | | os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id) |
|---|
| | | inference_pipline = pipeline( |
|---|
| | | task=Tasks.auto_speech_recognition, |
|---|
| | | model="damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch", |
|---|
| | | model="damo/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k", |
|---|
| | | output_dir=output_dir_job, |
|---|
| | | ) |
|---|
| | | audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx)) |
|---|
| | |
|---|
| | | # If text exists, compute CER |
|---|
| | | text_in = os.path.join(params["data_dir"], "text") |
|---|
| | | if os.path.exists(text_in): |
|---|
| | | text_proc_file = os.path.join(best_recog_path, "token") |
|---|
| | | text_proc_file = os.path.join(best_recog_path, "text") |
|---|
| | | compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer")) |
|---|
| | | |
|---|
| | | |
|---|
