diff --git a/packages/transformers/package.json b/packages/transformers/package.json
index 8b56e46b5..21c2e4458 100644
--- a/packages/transformers/package.json
+++ b/packages/transformers/package.json
@@ -57,7 +57,7 @@
   "dependencies": {
     "@huggingface/jinja": "^0.5.5",
     "@huggingface/tokenizers": "^0.1.2",
-    "onnxruntime-node": "1.24.2",
+    "onnxruntime-node": "1.25.0-dev.20260228-6e72d31970",
     "onnxruntime-web": "1.25.0-dev.20260221-b2a6e69e82",
     "sharp": "^0.34.5"
   },
diff --git a/packages/transformers/src/models/nemo_conformer_tdt/modeling_nemo_conformer_tdt.js b/packages/transformers/src/models/nemo_conformer_tdt/modeling_nemo_conformer_tdt.js
index b29359799..c26b08e75 100644
--- a/packages/transformers/src/models/nemo_conformer_tdt/modeling_nemo_conformer_tdt.js
+++ b/packages/transformers/src/models/nemo_conformer_tdt/modeling_nemo_conformer_tdt.js
@@ -57,7 +57,7 @@ function roundTs(value) {
 }
 
 /**
- * @param {Float32Array|number[]} logits
+ * @param {import('../../utils/tensor.js').DataArray} logits
  * @param {number} tokenId
  * @param {number} vocabSize
  * @returns {{ confidence: number, logProb: number }}
@@ -175,6 +175,7 @@ function resolveTransducerConfig(config, sessions) {
     const frameShiftS = transducerConfig.frame_shift_s ?? 0.01;
     const blankTokenId = transducerConfig.blank_token_id ?? 0;
     const encoderOutputLayout = transducerConfig.encoder_output_layout;
+    const encoderLengthDType = transducerConfig.encoder_length_dtype ?? 'int64';
     const decoderTokenDType = transducerConfig.decoder_token_dtype ?? 'int32';
     const decoderTokenLengthDType = transducerConfig.decoder_token_length_dtype ?? 'int32';
 
@@ -195,6 +196,11 @@ function resolveTransducerConfig(config, sessions) {
     if (encoderOutputLayout !== 'BDT' && encoderOutputLayout !== 'BTD') {
         throw new Error('Invalid `transformers.js_config.transducer.encoder_output_layout`: expected "BDT" or "BTD".');
     }
+    if (!['int32', 'int64'].includes(encoderLengthDType)) {
+        throw new Error(
+            'Invalid `transformers.js_config.transducer.encoder_length_dtype`: expected "int32" or "int64".',
+        );
+    }
     if (!['int32', 'int64'].includes(decoderTokenDType)) {
         throw new Error(
             'Invalid `transformers.js_config.transducer.decoder_token_dtype`: expected "int32" or "int64".',
@@ -216,6 +222,7 @@ function resolveTransducerConfig(config, sessions) {
         encoder_input_layout: transducerConfig.encoder_input_layout ?? 'BTF',
         encoder_output_layout: encoderOutputLayout,
         encoder_frame_layout: transducerConfig.encoder_frame_layout ?? 'BD1',
+        encoder_length_dtype: encoderLengthDType,
         decoder_token_dtype: decoderTokenDType,
         decoder_token_length_dtype: decoderTokenLengthDType,
         decoder: {
@@ -448,7 +455,9 @@ export class NemoConformerForTDT extends NemoConformerTDTPreTrainedModel {
                 } else {
                     length = inputFeatures.dims[1];
                 }
-                const lengthTensor = new Tensor('int64', BigInt64Array.from([BigInt(length)]), [1]);
+                const lengthTensor = this.transducer.encoder_length_dtype === 'int64'
+                    ? new Tensor('int64', BigInt64Array.from([BigInt(length)]), [1])
+                    : new Tensor('int32', new Int32Array([length]), [1]);
                 disposables.push(lengthTensor);
                 feeds[name] = lengthTensor;
                 continue;
diff --git a/packages/transformers/src/models/nemo_conformer_tdt/transducer_text.js b/packages/transformers/src/models/nemo_conformer_tdt/transducer_text.js
index d12a27553..d5cdb716b 100644
--- a/packages/transformers/src/models/nemo_conformer_tdt/transducer_text.js
+++ b/packages/transformers/src/models/nemo_conformer_tdt/transducer_text.js
@@ -167,6 +167,49 @@ export function buildTransducerDetailedOutputs(tokenizer, token_ids, token_times
 
     finalizeAndPushWord(words, current);
 
+    // Fallback for character-level tokenizers (e.g., Danish RNNT) where individual
+    // tokens lack ▁/Ġ word-start markers. Decode the full sequence to get the text
+    // with proper spaces, then use those spaces to detect word boundaries.
+    if (words.length <= 1 && tokens.length > 1) {
+        const fullDecoded = tokenizer
+            .decode(token_ids, { skip_special_tokens: true, clean_up_tokenization_spaces: false })
+            .trimStart();
+
+        words.length = 0;
+        current = null;
+        let pos = 0;
+
+        for (let j = 0; j < tokens.length; j++) {
+            let foundSpace = false;
+            while (pos < fullDecoded.length && /\s/.test(fullDecoded[pos])) {
+                foundSpace = true;
+                pos++;
+            }
+
+            const startsNewWord = j === 0 || foundSpace;
+            tokens[j].is_word_start = startsNewWord;
+            pos = Math.min(pos + tokens[j].token.length, fullDecoded.length);
+
+            if (!current || startsNewWord) {
+                finalizeAndPushWord(words, current);
+                current = {
+                    text: tokens[j].token,
+                    start: tokens[j].start_time,
+                    end: tokens[j].end_time,
+                    confs: tokens[j].confidence != null ? [tokens[j].confidence] : [],
+                };
+            } else {
+                current.text += tokens[j].token;
+                current.end = tokens[j].end_time;
+                if (tokens[j].confidence != null) {
+                    current.confs.push(tokens[j].confidence);
+                }
+            }
+        }
+
+        finalizeAndPushWord(words, current);
+    }
+
     const word_confidences = words.some((x) => x.confidence != null) ? words.map((x) => x.confidence ?? null) : null;
     let word_avg = null;
     if (word_confidences) {